Automation System for Students Attendance
Content
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 1
INTRODUCTION
Opening Doors
1.1 Overview of Biometric Technology
1
Automation System for Students’ Attendance using IRIS Recognition System
Identification of humans is a goal as ancient as humanity itself. As technology and services have developed in the modern world, human activities and transactions have proliferated in which rapid and reliable personal identification is required. Examples include passport control, computer login control, ban automatic teller machines and other transactions authori!ation, premises access control, and security systems generally. All such identification efforts share the common goals of speed, reliability and automation. "he use of biometric indicia for identification purposes requires that a particular biometric factor be unique for each individual that it can be readily measured, and that it is invariant over time. #iometrics such as signatures, photographs, fingerprints, voiceprints and retinal blood vessel patterns all have significant drawbac s. Although signatures and photographs are cheap and easy to obtain and store, they are Impossible to identify automatically a person with assurance, and are easily forged. Electronically recorded voiceprints are susceptible to changes in a person$s voice, and they can be counterfeited. %ingerprints or handprints require physical contact, and they also can be counterfeited and marred by artifacts. &uman iris on the other hand is an internal organ of the eye and is well protected, from the external environment. 'et it is easily visible from within one meter of distance ma es it a perfect biometric for an identification system with the ease of speed, reliability and automation. In this pro(ect, we are going to experiment, implement, and most importantly, loo into the theory behind an Iris )ecognition *ystem, which is not only related to the field of personal identification, and more specifically to the field of automated identification of humans by biometric indicia. #iometric authentication has been receiving extensive attention over the past decade with increasing demands in automated personal identification.
1.2 Objectives
"he main aim of our pro(ect is to build an application based on I)I* of a particular individual. "his application will help to the faculty of college+institutes to maintain the attendance of the students easily. "his pro(ect will also easily monitor the monthly attendance for each student and will reduce the teachers$ efforts.
1. !n"tomy of #$m"n Iris%
2
Automation System for Students’ Attendance using IRIS Recognition System
"he iris is a thin circular diaphragm, which lies between the cornea and the lens of the human eye. A side view of the iris is shown in %igure 1.1. "he iris is perforated close to its centre by a circular aperture nown as the pupil. "he function of the iris is to control the amount of light entering through the pupil, and this is done by the sphincter and the dilator muscles, which ad(ust the si!e of the pupil. "he average diameter of the iris is 1, mm, and the pupil si!e can vary from 1-. to /-. of the iris diameter. "he iris consists of a number of layers0 the lowest is the epithelium layer, which contains dense pigmentation cells. "he stromal layer lies above the epithelium layer, and contains blood vessels, pigment cells and the two iris muscles. "he density of stromal pigmentation determines the colour of the iris. "he externally visible surface of the multi1layered iris contains two !ones, which often differ in colour. An outer ciliary !one and an inner pupillary !one, and these two !ones are divided by the collarette 2 which appears as a !ig!ag pattern.
&ig$re 1.1 ' Anatomy of the human eye. %ormation of the iris begins during the third month of embryonic life. "he unique pattern on the surface of the iris is formed during the first year of life, and pigmentation of the stroma ta es place for the first few years. %ormation of the unique patterns of the iris is random and not related to any genetic factor. "he only characteristic that is dependent on genetics is the
3
Automation System for Students’ Attendance using IRIS Recognition System
pigmentation of the iris, which determines its colour. D$e to the e(igenetic n"t$re of iris ("tterns) the two eyes of "n in*ivi*$"l cont"in com(letely in*e(en*ent iris ("tterns) "n* i*entic"l twins (ossess $ncorrel"te* iris ("tterns.
4
Automation System for Students’ Attendance using IRIS Recognition System
Chapter ,
+RO,-CT D-&INITION
Getting Started
5
Automation System for Students’ Attendance using IRIS Recognition System
2.1 +roblem .t"tement
#uilding an application for managing students$ attendance using Iris )ecognition.
2.2 .co(e
"he modules to be covered by this application are as under0 1. 3elcome screen ,. 4atabase provider ,.1 5* Access ,., 6racle ,.7 *89 *erver 7. Connectivity :. 4ata fetch 5odules which are not in scope0 1. Currently this application will support images ta en from a digital camera. 2. "his application is no applicable to videos.
2. !((ro"ch
1. "a e the eye image of a student from a digital camera. ,. ;enerate the iris code and store it in the database for that particular student. 7. *tore bit pattern for all the students. :. In real time, capture the eye image of a student, generate the iris code for it and compare it with the existing database.
6
Automation System for Students’ Attendance using IRIS Recognition System
<. If the result of comparison is true, mar the attendance of that student otherwise as him to register.
2./ !ss$m(tions "n* Constr"ints
!ss$m(tions% End user will have 5icrosoft .=E" framewor 7.< installed in the machine. "he premises will also have a digital camera with minimum capacity of 7 mega pixels. Constr"ints% Camera should be properly mounted or its user should properly ta e the eye image of the student.
7
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 7
B!C01ROUND R-.-!RC#
8
Automation System for Students’ Attendance using IRIS Recognition System The motivation to work ahead
.1 2otiv"tion
%or verification of a person various parameters are used such as identity card, etc. #iometrics provides an alternative to these methods, or they can be used in combination multimodal>. %ingerprints, which are widely used, can be forged ?gummy fingers>. "he face changes over a period of time, even with the best algorithms face recognition ?for faces ta en one year apart> has error rates of about :7 to <- . , hand geometry is not distinctive enough to be used in large scale applications, hand1written signatures can be forged. "he iris is different for any two individuals even for identical twins@ 4=A is not unique among identical twins. "he process of capturing the iris image is not intrusive. Iris images can be computer matched more accurately than a face image, and it$s ac nowledged that iris recognition is more accurate than any other biometric technique, although there are some concerns regarding enrollment failure rates ?capturing the initial iris image to be used as a template for comparing with other images>. "he failure to enroll rate ?%"E> is the rate at which a biometric system fails to enroll a sub(ect$s biometric sample. "he process of enrolling a sub(ect for the first time requires some training. "hese are some of the reasons that ma e the iris recognition technology suitable for applications in which the user is cooperative.
.2 -3isting 4or5s
9
Automation System for Students’ Attendance using IRIS Recognition System
• #rea through wor to create the iris1recognition algorithms required for image acquisition and one1to1many matching was pioneered by Aohn ;. 4augman$s, Bh4, 6#E ?Cniversity of Cambridge Computer 9aboratory>. "hese were utili!ed to effectively debut commerciali!ation of the technology in con(unction with an early version of the Iris Access system designed and manufactured by DoreaEs 9; Electronics. 4augmanEs algorithms are the basis of almost all currently ?as of ,--F> commercially deployed iris1recognition systems. In tests where the matching thresholds areGfor better comparabilityGchanged from their default settings to allow a false1accept rate in the region of 1- H7 to 1-H:, the Iris Code false1re(ect rates are comparable to the most accurate single1finger fingerprint matchers. • Iris ;uard$s &omeland *ecurity #order Control has been operating an expellee trac ing system in the Cnited Arab Emirates ?CAE> since ,--1, when the CAE launched a national border1crossing security initiative. "oday, all of the CAEEs land, air and sea ports of entry are equipped with systems. All foreign nationals who possess a visa to enter the CAE are processed through iris cameras installed at all primary and auxiliary immigration inspection points. "o date, the system has apprehended over 77-,--- persons re1entering the CAE with fraudulent travel documents. • 6ne of three biometric identification technologies internationally standardi!ed by ICA6 for use in future passports ?the other two are fingerprint and face recognition> • Iris recognition technology has been implemented by #ioI4 "echnologies *A in Ba istan for C=&C) repatriation pro(ect to control aid distribution for Afghan refugees. )efugees are repatriated by C=&C) in cooperation with ;overnment of Ba istan, and they are paid for their travel. "o ma e sure people do not get paid more than once, their irises are scanned, and the system will detect the refugees on next attempt. "he database has more than 1.7 million iris code templates and around :--- registrations per day. "he one1to1many iris comparison ta es place within 1.< seconds against 1.7 million iris codes.
. Iris Recognition vers$s Other Biometric Technologies
10
Automation System for Students’ Attendance using IRIS Recognition System
"hree factors can be used for security0 something you now ?password or BI=>,
something you have ?smart to en or access card>, and something you are ?biometric>. #iometrics can be used alone or in con(unction with one of the other factors to strengthen the security chec . #iometric technology has advantages over both of the other factors in that the user does not need to remember anything or possess a physical to en in order to be identified. "o ens and cards can be lost, and passwords and BI=s can be forgotten or compromised. A biometric is only susceptible to forgery, which can be extremely difficult, depending on the biometric. Iris recognition falls into the physical biometric category as opposed to behavioral biometrics such as signatures. 6ther physical biometric technologies include fingerprinting, retinal scanning, spea er recognition, and facial scanning and hand geometry. "he =ational Center for *tate Courts ?=C*C> published information comparing these physical biometric methods.,- "he =C*C data is substantiated by a similar comparison table found at the IEEE Computer *ociety.,1 &ere are some highlights from both groups$ findings. &inger(rinting Iris recognition shares many characteristics with fingerprinting. #oth biometric technologies are reliable and very accurate, but iris recognition has a much lower error rate ?1 in 171,---> than fingerprinting ?1 in <--I>.,, ?"he =C*C defines error rate as the crossing point of the graphs of false positives and false negatives of a particular biometric.> #oth biometric methods can be used to verify that a person is who he or she claims to be and to identify a person by comparing the current biometric input to a large set of data that was previously recorded. According to the =C*C, false positives and false negatives are difficult to produce for both fingerprinting and iris recognition.,7 %alse acceptance rates are extremely low for iris recognition. "ests conducted through 4ecember ,--- had not resulted in a single false acceptance of an iris.,: #oth fingerprints and iris are stable physical characteristics that do not change with age. &owever, since older people tend to have drier s in, fingerprints can be more difficult to verify as a person ages. %ingerprinting hardware is generally less expensive than that for iris recognition, but recent technology is lowering costs of iris recognition devices.,< External factors can cause errors in both fingerprinting and iris recognition. %ingerprints can be affected by dirt, dryness and scarring. Iris recognition can be affected by lighting. #oth technologies are
11
Automation System for Students’ Attendance using IRIS Recognition System
reasonably well accepted by the user population, but fingerprinting was rated more intrusive than iris scanning.,J "his rating may be due to the requirement to ma e physical contact with a fingerprinting device. %ingerprinting may also carry some negative connotations due to its historical use in criminal investigations. "here are some health related advantages of iris recognition over fingerprinting. %ingerprinting requires physically touching a device each time the finger is presented for verification. In contrast, the iris template is created without any physical contact with the person whose iris is encoded. "he iris recognition process is, therefore, more appealing to those concerned with hygiene than is fingerprinting. %orgery is not as much of a ris with iris recognition as with fingerprinting. Although sophisticated fingerprinting technology is designed to detect false fingers, a person$s finger can be cut off or used for a mold much easier than an eyeball could be extracted and used for impersonation. In fact, the iris from a person$s extracted eye would not be usable for more than a few seconds.,K Iris recognition devices can also detect the dilating pupil to ensure that the eye is live. Retin"l .c"nning )etinal scanning is often confused with iris recognition, but they are very different biometric technologies. "he retina is located at the bac of the eye and contains distinctive vascular patterns that can be used for identification and verification. )etinal scanning is the only biometric that is more reliable than iris recognition. "he error rate for retinal scanning is 101-,---,--- compared to the iris recognition error rate of 10171,---. ,/ "he retinal scanning process is different from iris recognition and does not involve an IrisCode. #oth retinal and iris technologies are extremely accurate and reliable and have very low false acceptance rates. 6pinions seem to differ on which feature, iris or retina, is more reliable to use throughout life. According to Aohn 5arshall of )etinal "echnologies, L"he iris is harder to map as an image because it fluctuates based on the si!e of the pupil, and drug or medicinal use, and age. "he retina stays constant throughout your life, unless you have glaucoma or diabetes.M,F "rue, the iris is not fully shaped until about eight months of age, but after that age, it is commonly believed to be stable.
12
Automation System for Students’ Attendance using IRIS Recognition System
As depicted in the movie, L5inority )eport,M retinal scanning is a much more intrusive process than iris recognition. A retinal scanning sub(ect must stay very still, with the eye at a distance of no more than 7 inches from the scanner, whereas iris recognition can be accomplished with the sub(ect at a distance of up to about , feet from the camera. Beople wearing glasses must remove them for a retinal scan. %or iris recognition, the =ational Bhysical 9aboratory ?=B9> tests found that glasses can ma e enrollment more difficult, but they can remain in place for verification without causing difficulty.7- "he =B9 tests revealed difficulty in enrolling a blind person$s iris because the system required both eyes to be enrolled.71 4epending upon the nature of the blindness, enrollment of two eyes using retinal scanning might also be prohibitive. =o =B9 data was reported for retinal scans of blind eyes. =either technology has been inexpensive in the past, but recent developments are bringing prices down for both iris recognition and retinal scanning. )etinal scans are probably most appropriate for applications that require the highest levels of security, where the sub(ect is very cooperative and patient, or is required by law to succumb to the scan. .(e"5er Recognition 6f the physical biometric technologies discussed in the =C*C comparison, spea er recognition ran s highest in user acceptance, and is easier to use and less expensive than iris recognition. 3ith an error rate of 1 in <-, spea er recognition is much less accurate than iris recognition.7, false negatives are easy to produce, and the errors can occur due to noise and colds. *pea er recognition could be used to verify a person$s identity, comparing to a previously stored template for a person, but is not recommended for identification. Iris recognition is recommended for both verification and identification.77 &"ci"l Recognition *imilar to iris recognition, facial recognition requires a sub(ect to present his or her face to a camera. #oth technologies are non1intrusive, but they differ in that the sub(ects in facial recognition need not now their identity is being captured on camera. "his aspect can be beneficial in areas where it is important to confirm identity without the sub(ect$s nowledge, but the anonymity with which a facial image can be captured also raises a privacy issue that is not
13
Automation System for Students’ Attendance using IRIS Recognition System
present with iris recognition. Iris recognition is more reliable than facial recognition.7: "he =B9 study cites a false accept rate of 101-- for facial recognition versus 101., million for iris recognition. #"n* 1eometry "he =C*C chart lists hand geometry as one of the easier to use biometric technologies, but it is not as accurate as either iris recognition or retinal scanning. "he error rate for hand geometry is 1 in <-- compared to 1 in 171,--- for iris recognition. Another drawbac of hand geometry technology is that it is relatively easy to produce a false negative, since hand features are not distinctive. "herefore, the technology is not well suited for identification. It should wor well enough for verification as long as the device can recogni!e a fa e hand. Cnli e the iris, hand characteristics could change over time due to scars and growth patterns. &and geometry has the same hygiene issue as fingerprinting.
14
Automation System for Students’ Attendance using IRIS Recognition System
Chapter :
6IT-R!TUR- .UR7-8
15
Automation System for Students’ Attendance using IRIS Recognition System Expanding horizon
/.1 Rese"rch of 7"rio$s !$thors%
,. D"$gm"n. #ow iris recognition wor5s. +rocee*ings of 2992 Intern"tion"l Conference on Im"ge +rocessing) 7ol. 1) 2992. Algorithms developed by the author for recogni!ing persons by their iris patterns have been tested wherein they deal in combinatorial complexity of phase information across different persons who spans about ,:F degrees of freedom and generates discrimination entropy of about 7., bits+mm, over the iris, enabling real1time decisions about personal identity with extremely high confidence. "he high confidence levels are important because they allow very large databases to be searched exhaustively ?one1to1many identification mode.> without ma ing false matches, despite so many chances. C. Tisse) 6. 2"rtin) 6. Torres) 2. Robert. +erson i*entific"tion techni:$e $sing h$m"n iris recognition. Intern"tion"l Conference on 7ision Interf"ce) C"n"*") 2992. "his paper examines a new iris recognition system that implements ?I> gradient decomposed &ough transform + integral1differential operators combination for iris locali!ation and ?II> the Lanalytic imageM concept ?,4 &ilbert transform> to extract pertinent information from iris texture. All these image1processing algorithms have been validated on noised real iris
16
Automation System for Students’ Attendance using IRIS Recognition System
images database. "he proposed innovative technique is computationally effective as well as reliable in terms of recognition rates. 4. 0ong) D. ;h"ng. !cc$r"te iris segment"tion b"se* on novel reflection "n* eyel"sh *etection mo*el. +rocee*ings of 2991 Intern"tion"l .ym(osi$m on Intelligent 2$ltime*i") 7i*eo "n* .(eech +rocessing) #ong 0ong) 2991. In this paper, a novel noise detection model is proposed for accurate segmentation of an iris. Eyelash, eyelid and reflection are three main noises. Eyelid had been solved by traditional eye model@ however, eyelash and reflection are not been regarded. "o determinate a pixel in an eyelash, their model follows the three criterions0 1> separable eyelash condition, ,> non1 informative condition and 7> connective criterion. "he first and second condition handles separable and multiple eyelashes respectively. "he last criterion avoids misclassification of strong iris texture as a single and separable eyelash. %or reflection, a threshold detects strong reflection points and the wea reflection points around the strong points are determined by connective criterion and statistical test. 6. 2") 8. 4"ng) T. T"n. Iris recognition $sing circ$l"r symmetric filters N"tion"l 6"bor"tory of +"ttern Recognition) Instit$te of !$tom"tion) Chinese !c"*emy of .ciences) 2992. &ere the authors deal in a ban of circular symmetric filter is used to capture local iris characteristics to from a fix length feature vector for iris recognition. +. B$rt) -. !*el son. The l"(l"ci"n (yr"mi* "s " com("ct im"ge co*e. I--- Tr"ns"ctions on Comm$nic"tions) 7ol. CO2< 1) No. /) 1=> "hey describe a technique for image encoding in which local operators of many scales but identical shape serve as the basis functions. "he representation differs from established techniques in that the code elements are locali!ed in spatial frequency as well as in space. C. #. D"o$5) 6. !. -l<-sber) &. D. 0"mmo$n "n* 2. !. !l !l"o$i) Iris Recognition) I--I..+IT 2992) 2"rr"5esh.
17
Automation System for Students’ Attendance using IRIS Recognition System
In this paper, a novel technique is developed to create an Iris )ecognition *ystem. "hey deal in a fusion mechanism that amalgamates both, a Canny Edge 4etection scheme and a Circular &ough "ransform, to detect the iris$ boundaries in the eye$s digital image. "his is followed by the application of the &aar wavelet in order to extract the deterministic patterns in a person$s iris in the form of a feature vector. #y comparing the quanti!ed vectors using the &amming 4istance operator, we determine finally whether two irises are similar. T. 6ee. Im"ge re(resent"tion $sing 2D 1"bor w"velets. I--- Tr"ns"ctions of +"ttern !n"lysis "n* 2"chine Intelligence) 7ol. 1>) No. 19) 1==?. "his paper extends to two dimensions the frame criterion developed by 4aubechies for one1dimensional wavelets, and it computes the frame bounds for the particular case of ,4 ;abor wavelets. D. &iel*. Rel"tions between the st"tistics of n"t$r"l im"ges "n* the res(onse. +ro(erties of cortic"l cells. ,o$rn"l of the O(tic"l .ociety of !meric") 1=>@. =atural images are not random@ instead, they exhibit statistical regularities. Assuming that our vision is designed for tas s on natural images, computation in the visual system should be optimi!ed for such regularities. )ecent theoretical investigations along this line have provided many insights into the visual response properties in the early visual system. In this article we review both the nown statistical regularities of natural images, the extent to which low1level vision might be adapted to them, and the recent development in theoretical models to explain this relationship.
/.2 2etho* Use* &or Im(lement"tion%
/.2.1 -*ge Detection Edge detection is a well1developed field on its own within image processing. )egion boundaries and edges are closely related, since there is often a sharp ad(ustment in intensity at the region boundaries. Edge detection techniques have therefore been used as the base of another segmentation technique. "he edges identified by edge detection are often disconnected. "o segment an ob(ect from an image however, one needs closed region boundaries.
/.2.2 .egment"tion
18
Automation System for Students’ Attendance using IRIS Recognition System
In computer vision, segment"tion refers to the process of partitioning a digital image into multiple segments ?sets of pixels, also nown as super pixels>. "he goal of segmentation is to simplify and+or change the representation of an image into something that is more meaningful and easier to analy!e. Image segmentation is typically used to locate ob(ects and boundaries ?lines, curves, etc.> in images. 5ore precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. "he result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image ?li e edge detection>. Each of the pixels in a region is similar with respect to some characteristic or computed property, such as color, intensity, or texture. Ad(acent regions are significantly different with respect to the same characteristic?s>.
/.2. 2e*i"n &ilter In signal processing, it is often desirable to be able to perform some ind of noise reduction on an image or signal. "he me*i"n filter is a nonlinear digital filtering technique, often used to remove noise. *uch noise reduction is a typical pre1processing step to improve the results of later processing ?for example, edge detection on an image>. 5edian filtering is very widely used in digital image processing because under certain conditions, it preserves edges whilst removing noise. "he main idea of the median filter is to run through the signal entry by entry, replacing each entry with the median of neighboring entries. "he pattern of neighbors is called the NwindowN, which slides, entry by entry, over the entire signal. %or 14 signal, the most obvious window is (ust the first few preceding and following entries, whereas for ,4 ?or higher1 dimensional> signals such as images, more complex window patterns are possible ?such as NboxN or NcrossN patterns>. =ote that if the window has an odd number of entries, then the median is simple to define0 it is (ust the middle value after all the entries in the window are sorted numerically. %or an even number of entries, there is more than one possible median. /.2./ Thinning
19
Automation System for Students’ Attendance using IRIS Recognition System
6ptical scanning of the roc inscription yields an image ?file of pixels> that forms the raw input to the 6ptical Character )ecognition *ystem. "he output is the set of recogni!ed characters. Breprocessing is the first phase of document analysis. "he purpose of preprocessing is to improve the quality of the image being processed. It ma es the subsequent phases of image processing li e recognition of characters easier. Thinning is one of the preprocessing methods. In thinning, the image regions are reduced to one1pixel width characters. "hinning is an image preprocessing operation performed to ma e the image crisper by reducing the binary1valued image regions to lines that approximate the s eletons of the region. "hinning cleans the image so that only reduced amount of data needs to be processed in the next image processing stage. *hape analysis could be done easily. "hinning algorithms should perform thinning effectively by successive deletion of dar points ?i.e. changing them to white points> along the edges of the pattern until it is thinned to a line. An effective thinning algorithm is one that can ideally compress data, eliminate local noise without introducing distortions of its own. #ut the ey goal is to retain significant features of the pattern. "here are two types of thinning algorithms 1. *equential thinning algorithms ,. Barallel thinning algorithms In O1P, result of nth iteration depends on result of ?n11>th iteration as well as pixels already processed in the nth iteration. In O,P, deletion of pixels in of nth iteration depends only on the result that remains after ?n11>th iteration. 3e consider only the type O,P algorithms here.
20
Automation System for Students’ Attendance using IRIS Recognition System
Chapter <
R-AUIR-2-NT .+-CI&IC!TION
21
Automation System for Students’ Attendance using IRIS Recognition System
All that system needs
B.1 &$nction"lity Re:$irements
"he system is built to ease the management of students$ attendance. In($t% "he input given to the system will be the eye images of the student. Beh"vior% "he iris is extracted from the eye image and its iris code is generated. "his iris code is compared with those in the database. O$t($t% If iris pattern matched, mar the attendance of that student.
22
Automation System for Students’ Attendance using IRIS Recognition System B.2 #"r*w"re !n* .oftw"re Re:$irements
#"r*w"re Re:$irements 1. 5inimum0 1.J ;&! CBC, <1, 5# )A5, 1-,:xKJ/ display, <:-- )B5 hard dis . ,. )ecommended0 ,., ;&! or higher CBC, 1-,: 5# or more )A5, 1,/-x1-,: display, K,-- )B5 or higher hard dis . 7. 4igital Camera with minimum resolution of < mega pixels. .oftw"re Re:$irements 1. *89 *erver ,--< ,. "urbo C+CII 7. .=E" %ramewor 7.< Qersion number 1 :<-J.7-
B. +rogr"mming -nvironment Re:$irements
.$((orte* D"t"b"ses 1. CA*IA ?Chinese Academy of *ciences 4atabases> ,. #A"& ?Broduced #y Cniversity of #ath> 7. C#I)I* .$((orte* O(er"ting .ystems 1. 5icrosoft 3indows RB ,. 5icrosoft 3indows Qista 6"ng$"ges
23
Automation System for Students’ Attendance using IRIS Recognition System
1. CS 7.< ,. C 7. CII
Chapter J
+RO,-CT +6!NNIN1
24
Automation System for Students’ Attendance using IRIS Recognition System
Laying the foundation
?.1 !ctivity +l"n
.che*$ling 1C Re:$irement 1"thering
.r. No.
N"me of .$b mo*$le
No. of ho$rs
&rom D"te
To D"te
25
Automation System for Students’ Attendance using IRIS Recognition System
1 2 6iter"t$re .$rvey .t$*y of !lgorithm D-3isting IrisC 2C Re:$irement !n"lysis .r. No. 1 2 N"me of .$b mo*$le .co(e Definition &e"sibility .t$*y No. of ho$rs 9= 19 &rom D"te >th .e(tember)9= Bth .e(tember)9= To D"te 1/th .e(tember) 9= 19th .e(tember) 9= 9 /> 1>th !$g$st) 9= 2>th !$g$st) 9= 9th!$g$st) 9= 1Bth .e(tember) 9=
C .ystem Design
.r. No. 1 2
N"me of .$b mo*$le .t$*y of !lgorithms Im(lement"tion of !lgorithms Design of 1UIEs .t$*y of Connectivity Testing the system on *ifferent im"ge form"t
No. of ho$rs 9= 129
&rom D"te 1=th .e(tember) 9= 1>th December) 9=
To D"te 11th October) 9= 2Bth ,"n$"ry) 19
>9 B
12th &ebr$"ry)19 1st 2"rch)19
2>th &ebr$"ry)19 >th 2"rch)19
/
B
/9
12th 2"rch)19
2>th 2"rch)19
? @
Other !s(ects U26 Design
9 9=
1Bth &ebr$"ry) 19 ?th ,"n$"ry) 19
1Bth 2"rch) 19 9th ,"n$"ry) 19
/C .oftw"re Testing
26
Automation System for Students’ Attendance using IRIS Recognition System
Chapter K
D-.I1N
27
Automation System for Students’ Attendance using IRIS Recognition System
Expressing ideas
@.1 Design Overview
Bloc5 Di"gr"m
28
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @.2.1 Bloc5 Di"gr"m
@.2 U26 Di"gr"ms @.2.1 Use C"se Di"gr"m
29
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. .1 Use C"se Di"gr"m
@.2.2 .e:$ence Di"gr"m
30
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. .2 .e:$ence Di"gr"m
@.2. Comm$nic"tion Di"gr"m
31
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. ./ Comm$nic"tion Di"gr"m
@.2./ De(loyment Di"gr"m
&ig$re @. .B De(loyment Di"gr"m
32
Automation System for Students’ Attendance using IRIS Recognition System
Chapter /
#O4 .8.T-2 4OR0.
ay it goes!
33
Automation System for Students’ Attendance using IRIS Recognition System >.1 .ystem Overview
"he entire system wor s (ust li e any other application using navigation controls. "he end user can navigate from one page to another and can view image and other details of the entered roll number as he wishes. "he application spans the following pages in accordance with the end user selection0 1. ,. 7. 3elcome Bage *election of the required tas 2 register+recognition If register is selected 7.1 %ill the details of the student 7., Capture his image 7.7 ;enerate the iris code and store in database :. If recognition is selected :.1 Enter the roll number to be verified. :., Capture the image :.7 ;enerate the iris code and compare with the database :.: If verified 2 mar the attendance :.< Else as him to register. <. Qiew the attendance sheet of the whole class. >.1.1 Registering " st$*ent Initially the database of the students has to be prepared, for this purpose the students have to register themselves.
34
Automation System for Students’ Attendance using IRIS Recognition System
"he steps for registering a student are 2 1. ;o to &ome page Computer 4epartment )egister. ,. %ill the details of that student including his =ame, )oll number, 'ear, #ranch, Contact number, Address, E1mail id.
7. "a e the eye image of the student with the specified camera. :. #rowse the photo of the student whose information is filled. <. Bress LCreate irisM. J. "he iris code will be generated. K. Bress the L*ubmitM button. "hus the iris code will be generated for the eye image of that student and will be stored with his personal information.
35
Automation System for Students’ Attendance using IRIS Recognition System
>.1.2 RecogniFing " st$*ent %or recogni!ing a student for mar ing his attendance 2 1. ;o to &ome page Computer 4epartment )ecognition. ,. Enter the roll number of the student you want to recogni!e.
7. Bress L)ecognitionM.
36
Automation System for Students’ Attendance using IRIS Recognition System
:. "he student information will be displayed. <. Bress L#rowseM to select the recent image of the student. J. Bress LCreate irisM. K. "he iris code will be generated. /. Bress LverifyM. F. According to the, the result will be displayed. 1-. If the image is already stored, then is shows LQalid *tudent. Attendance mar ed.M If not, then it as s to L)egisterM.
37
Automation System for Students’ Attendance using IRIS Recognition System
>.2 4or5ing of the system
>.2.1 6ogin +"ge "he welcome page consists of various tabs that allow a user to navigate through the website. "he user can view the contents of the various tabs provided. "he user can enter to the student attendance system using the tab in LComputer 4epartmentM. >.2.2 .election of the re:$ire* t"s5 ' registerGrecognition Bage =ame 0 3elcome Computer 4epartment Input 6utput >.2. 0 Clic on )egister+ )ecognition 0 )egister+)ecognition Bage .electing " (ro(er ste(%
38
Automation System for Students’ Attendance using IRIS Recognition System
>.2. .1 If register is selecte* < %ill the details of the student Bage =ame0 3elcome Computer 4epartment )egister Input 0 )oll no., =ame, Address, Contact, E1mail id, 'ear. >.2. .2 C"(t$re his im"ge Bage =ame0 3elcome Computer 4epartment )egister Input 6utput 0 Eye image. 0 )egister =ew Cser window appears.
>.2. . 1ener"te the iris co*e "n* store in *"t"b"se Bage =ame0 3elcome Computer 4epartment )egister Input 6utput >.2./ 0 Clic on )egister 0 Iris code is generated and information is stored in the database. Reselection of .te(1 >.2./.1 If recognition is selecte* < Enter the roll number to be verified. Bage =ame0 3elcome Computer 4epartment )egister Input 6utput 0 #utton clic to select recognition of the specified roll number. 0 Bage with details of the student.
>.2./.2 C"(t$re the im"ge Capture the image of the student using the digital camera as specified.
39
Automation System for Students’ Attendance using IRIS Recognition System
>.2./. 1ener"te the iris co*e "n* com("re with the *"t"b"se Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 *elect on the current image ta en and clic o . 0 Iris code for the new image is generated and is compared with the database.
>.2././ If verifie* ' m"r5 the "tten*"nce Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 Image for recognition. 0 Qerified and attendance mar ed.
>.2./.B -lse "s5 him to register. Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 Image for recognition. 0 =ot verified. )egister if not present in the database.
>.2.B 7iew the "tten*"nce sheet of the whole cl"ss. Bage =ame0 3elcome Computer 4epartment )ecognition Attendance *heet Input 6utput 0 Clic on 3elcome Computer 4epartment )ecognition Attendance *heet 0 Attendance *heet for whole class is appearing.
>. .o$rce co*e 2o*$les%
IC .egment"tion
40
Automation System for Students’ Attendance using IRIS Recognition System
+T %unction name 0 segmentUimage?> input output 0 17T17 bloc of the input image in an array form 0 "he entire bloc flagged to be used for further calculations or left to be neglected further. T+ void segmentUimage?> V int iW-,(W-,xW-,yW-,avgW-,countW-@ for?iW-@iX#96CD*@iII> for?(W-@(X#96CD*@(II> V avgW-@ countW-@ for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII> avgWimageOxPOyPIavg@ avgWavg+?3I=T3I=>@ for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII>
41
Automation System for Students’ Attendance using IRIS Recognition System
V if??imageOxPOyPY?avg11->>ZZ?imageOxPOyPX?avgI1->>> countII@ [ if?countY1,1> V for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII> imageOxPOyPW,<<@ [ [ [
IIC Bin"rise Im"ge +T %unction name 0 binariseUimage input 0 17T17 bloc of the image array
4escription 0 Each pixel is either mar ed as - or ,<< depending upon its intensity output 0 17T17 array with each value either as - or ,<<
42
Automation System for Students’ Attendance using IRIS Recognition System
T+ void binariseUimage?> V int iW-,(W-,xW-,yW-,midUvalueW-,upperUboundW-@ for?iW-@iX#96CD*@iII> for?(W-@(X#96CD*@(II> V for?xWiT3I=@xX?iT3I=>I3I=@xII> for?yW(T3I=@yX?(T3I=>I3I=@yII> V numOupperUboundPWimageOxPOyP@ upperUboundII@ [ midUvalueWsort?upperUbound>@ for?xWiT3I=@xX?iT3I=>I3I=@xII> for?yW(T3I=@yX?(T3I=>I3I=@yII> V if?imageOxPOyPXmidUvalue> imageOxPOyPW-@
43
Automation System for Students’ Attendance using IRIS Recognition System
else imageOxPOyPW,<<@ [ midUvalueW-@ upperUboundW-@ [ [
IIIC 2e*i"n &ilter +T %unction name 0 medianUfilter?> input output T+ void medianUfilter?> V int xW-,yW-,midUvalueW-,upperUboundW-@ for?xW1@xX7--@xII> for?yW1@yX7--@yII> V upperUboundW-@
44
0 17 T 17 bloc array of the input image array 0 17 T 17 bloc array with noise eliminated using median filtering
Automation System for Students’ Attendance using IRIS Recognition System
numOupperUboundPWimageOx11POy11P@ numOupperUboundIIPWimageOx11POyP@ numOupperUboundIIPWimageOx11POyI1P@ numOupperUboundIIPWimageOxPOy11P@ numOupperUboundIIPWimageOxPOyP@ numOupperUboundIIPWimageOxPOyI1P@ numOupperUboundIIPWimageOxI1POy11P@ numOupperUboundIIPWimageOxI1POyP@ numOupperUboundIIPWimageOxI1POyI1P@ upperUboundII@ midUvalueWsort?upperUbound>@ imageOxPOyPWmidUvalue@ [ [
45
Automation System for Students’ Attendance using IRIS Recognition System
Chapter F
46
Automation System for Students’ Attendance using IRIS Recognition System
T-.TIN1
Learning from mistakes
=.1 .oftw"re Testing
*oftware "esting is an empirical investigation conducted to provide sta eholders with information about the quality of the product or service under test, with respect to the context in which it is intended to operate. "his includes, but is not limited to, the process of executing a program or application with the intent of finding software bugs. It can also be stated as the process of validating and verifying that a software program+application+product meets the business and technical requirements that guided its design and development, so that it wor s as expected and can be implemented with the same characteristics.
47
Automation System for Students’ Attendance using IRIS Recognition System =.2 Testing "rtif"cts
*oftware testing process can produce several artifacts Test c"se A test case in software engineering normally consists of a unique identifier, requirement references from a design specification, preconditions, events, a series of steps ?also nown as actions> to follow, input, output, expected result, and actual result. Clinically defined a test case is an input and an expected result. "his can be as pragmatic as Efor condition x your derived result is yE, whereas other test cases described in more detail the input scenario and what results might be expected. Test scri(t "he test script is the combination of a test case, test procedure, and test data. Initially the term was derived from the product of wor created by automated regression test tools. "oday, test scripts can be manual, automated, or a combination of both. Test *"t" "he most common test manually or in automation is retesting and regression testing. In most cases, multiple sets of values or data are used to test the same functionality of a particular feature. All the test values and changeable environmental components are collected in separate files and stored as test data. It is also useful to provide this data to the client and with the product or a pro(ect. Test s$ite "he most common term for a collection of test cases is a test suite. "he test suite often also contains more detailed instructions or goals for each collection of test cases. It definitely contains a section where the tester identifies the system configuration used during testing. A group of test cases may also contain prerequisite states or steps, and descriptions of the following tests. Test (l"n
48
Automation System for Students’ Attendance using IRIS Recognition System
A test specification is called a test plan. "he developers are well aware what test plans will be executed and this information is made available to the developers. "his ma es the developers more cautious when developing their code. "his ensures that the developer$s code is not passed through any surprise test case or test plans. Test h"rness "he software, tools, samples of data input and output, and configurations are all referred to collectively as a test harness.
=. .ystem ($t to Test =. .1 Testing .n"(shots
49
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1.1 Test C"ses.
50
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1.2 R$n Test.
51
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1. 7"li*"tion Test.
=. .2 Testing Re(ort
52
Automation System for Students’ Attendance using IRIS Recognition System
.$bject 1 Browsing thro$gh the website 1.1 !$thentic"tion .$bject% 9ogin .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 1.1.1 *teps .te( N"me Descri(tion -3(ecte* Res$lt *tep 1 #rowsing through the web 3hen the web site name is pages. given in the address bar the home page is opened. *tep , Clic ing on About 5AE tab. 3hen clic ed on NAbout 5AEN "ab home page is displayed. *tep 7 Clic ing on Infrastructure tab. 3hen clic ed on N InfrastructureN "ab Infrastructure page is opened. *tep : Clic ing on Blacement Cell 3hen clic ed on N Blacement tab. CellN "ab Blacement Cell page is opened. *tep < Clic ing on Contact Cs tab. 3hen clic ed on N Contact CsN "ab Contact Cs page is opened. *tep J *tep K Clic ing on department Computer 3hen clic ed on N Computer departmentN "ab "wo sub parts are opened. Chec the feed bac in the %eed bac is accepted in the web page. web page.
1.2 Register New .t$*ent .$bject% 9ogin .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 1.,.1 *teps .te( N"me Descri(tion *tep 1 Entering )oll =umber student. *tep , Entering =ame of student.
53
-3(ecte* Res$lt of 6nly numbers are accepted, characters are not allowed. Characters are allowed.
Automation System for Students’ Attendance using IRIS Recognition System
*tep 7 Entering E1mail id of student. 6nly the E1mail ids accrding to 4=* system are accepted otherwise displays the error msg. Entering Address of student . "he address of the student is accepted. Entering Contact no of the 6nly =umbers can be entered. student.
*tep : *tep <
2 .chem" Det"ils 2.1 +roce*$res .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.1.1 *teps .te( N"me Descri(tion *tep 1 Bress browse in the registration web page. *tep , *elect particular eye image of the respective student. *tep 7 Bress create iris code. *tep : Bress submit.
-3(ecte* Res$lt "he dialog box for choosing the image is displayed. "he eye image is displayed. "he processing of selected eye image ta es place and iris code is generated. "he generated iris code along with the entered information of the student is inserted into the database.
2.2 Recognition of " st$*ent .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.7.1 *teps .te( N"me Descri(tion -3(ecte* Res$lt *tep 1 Enter the )oll number to be "he entered information of the recognised and pressed give roll number is displayed. recognise.
54
Automation System for Students’ Attendance using IRIS Recognition System
*tep , *tep 7 Bress #rowse. Bress Qerify. "he dialog box for selecting a particular eye image is displayed. "he iris code for the newly given eye image is generated and compared with the already existing entries.
2. 7iew the tot"l "tten*"nce .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.7.1 *teps .te( N"me Descri(tion *tep 1 "est the database. *tep ,
-3(ecte* Res$lt database is opened and attendance sheet is displayed. Qiew the present status of the Bresent *tatus of the student is student. displayed.
55
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 1-
CONC6U.ION
Leap towards the new "eginning
"he system for attendance management wor s efficiently for various types of image such as .bmp, .(peg, and other formats. "his system is also built up to show the total attendance of the students. As a website, this system can be uploaded on the internet and can be viewed as a website. "hus, in total this system can be described as1 !$tom"te* 2 As it successfully monitors the attendance.
56
Automation System for Students’ Attendance using IRIS Recognition System
.ec$re* 2 #uilt in A*B.=et ma es it secured website. &le3ible 2 As it can run on different image format. A$ic5 2 As the response time of the system is very less.
57
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 11
&UTUR- .CO+-
Thinking out of the "ox
3e have wor ed sufficiently on still images for iris recognition of a person and applied it for managing the attendance. "his concept of iris recognition for still images can be further extended to 1 1. Iris recognition using a real time video. ,. #uilt a complete product to ma e it as fully fledged software. 7. "he developed application should be able to support a large database. :. "he response time for the system supporting large database should be very less.
58
Automation System for Students’ Attendance using IRIS Recognition System
At last, the unique biometric identification technique of I)I* recognition should be applicable to a variety of real time systems for Qerification, Identification, *ecurity and *afety purposes.
59
Chapter 1
INTRODUCTION
Opening Doors
1.1 Overview of Biometric Technology
1
Automation System for Students’ Attendance using IRIS Recognition System
Identification of humans is a goal as ancient as humanity itself. As technology and services have developed in the modern world, human activities and transactions have proliferated in which rapid and reliable personal identification is required. Examples include passport control, computer login control, ban automatic teller machines and other transactions authori!ation, premises access control, and security systems generally. All such identification efforts share the common goals of speed, reliability and automation. "he use of biometric indicia for identification purposes requires that a particular biometric factor be unique for each individual that it can be readily measured, and that it is invariant over time. #iometrics such as signatures, photographs, fingerprints, voiceprints and retinal blood vessel patterns all have significant drawbac s. Although signatures and photographs are cheap and easy to obtain and store, they are Impossible to identify automatically a person with assurance, and are easily forged. Electronically recorded voiceprints are susceptible to changes in a person$s voice, and they can be counterfeited. %ingerprints or handprints require physical contact, and they also can be counterfeited and marred by artifacts. &uman iris on the other hand is an internal organ of the eye and is well protected, from the external environment. 'et it is easily visible from within one meter of distance ma es it a perfect biometric for an identification system with the ease of speed, reliability and automation. In this pro(ect, we are going to experiment, implement, and most importantly, loo into the theory behind an Iris )ecognition *ystem, which is not only related to the field of personal identification, and more specifically to the field of automated identification of humans by biometric indicia. #iometric authentication has been receiving extensive attention over the past decade with increasing demands in automated personal identification.
1.2 Objectives
"he main aim of our pro(ect is to build an application based on I)I* of a particular individual. "his application will help to the faculty of college+institutes to maintain the attendance of the students easily. "his pro(ect will also easily monitor the monthly attendance for each student and will reduce the teachers$ efforts.
1. !n"tomy of #$m"n Iris%
2
Automation System for Students’ Attendance using IRIS Recognition System
"he iris is a thin circular diaphragm, which lies between the cornea and the lens of the human eye. A side view of the iris is shown in %igure 1.1. "he iris is perforated close to its centre by a circular aperture nown as the pupil. "he function of the iris is to control the amount of light entering through the pupil, and this is done by the sphincter and the dilator muscles, which ad(ust the si!e of the pupil. "he average diameter of the iris is 1, mm, and the pupil si!e can vary from 1-. to /-. of the iris diameter. "he iris consists of a number of layers0 the lowest is the epithelium layer, which contains dense pigmentation cells. "he stromal layer lies above the epithelium layer, and contains blood vessels, pigment cells and the two iris muscles. "he density of stromal pigmentation determines the colour of the iris. "he externally visible surface of the multi1layered iris contains two !ones, which often differ in colour. An outer ciliary !one and an inner pupillary !one, and these two !ones are divided by the collarette 2 which appears as a !ig!ag pattern.
&ig$re 1.1 ' Anatomy of the human eye. %ormation of the iris begins during the third month of embryonic life. "he unique pattern on the surface of the iris is formed during the first year of life, and pigmentation of the stroma ta es place for the first few years. %ormation of the unique patterns of the iris is random and not related to any genetic factor. "he only characteristic that is dependent on genetics is the
3
Automation System for Students’ Attendance using IRIS Recognition System
pigmentation of the iris, which determines its colour. D$e to the e(igenetic n"t$re of iris ("tterns) the two eyes of "n in*ivi*$"l cont"in com(letely in*e(en*ent iris ("tterns) "n* i*entic"l twins (ossess $ncorrel"te* iris ("tterns.
4
Automation System for Students’ Attendance using IRIS Recognition System
Chapter ,
+RO,-CT D-&INITION
Getting Started
5
Automation System for Students’ Attendance using IRIS Recognition System
2.1 +roblem .t"tement
#uilding an application for managing students$ attendance using Iris )ecognition.
2.2 .co(e
"he modules to be covered by this application are as under0 1. 3elcome screen ,. 4atabase provider ,.1 5* Access ,., 6racle ,.7 *89 *erver 7. Connectivity :. 4ata fetch 5odules which are not in scope0 1. Currently this application will support images ta en from a digital camera. 2. "his application is no applicable to videos.
2. !((ro"ch
1. "a e the eye image of a student from a digital camera. ,. ;enerate the iris code and store it in the database for that particular student. 7. *tore bit pattern for all the students. :. In real time, capture the eye image of a student, generate the iris code for it and compare it with the existing database.
6
Automation System for Students’ Attendance using IRIS Recognition System
<. If the result of comparison is true, mar the attendance of that student otherwise as him to register.
2./ !ss$m(tions "n* Constr"ints
!ss$m(tions% End user will have 5icrosoft .=E" framewor 7.< installed in the machine. "he premises will also have a digital camera with minimum capacity of 7 mega pixels. Constr"ints% Camera should be properly mounted or its user should properly ta e the eye image of the student.
7
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 7
B!C01ROUND R-.-!RC#
8
Automation System for Students’ Attendance using IRIS Recognition System The motivation to work ahead
.1 2otiv"tion
%or verification of a person various parameters are used such as identity card, etc. #iometrics provides an alternative to these methods, or they can be used in combination multimodal>. %ingerprints, which are widely used, can be forged ?gummy fingers>. "he face changes over a period of time, even with the best algorithms face recognition ?for faces ta en one year apart> has error rates of about :7 to <- . , hand geometry is not distinctive enough to be used in large scale applications, hand1written signatures can be forged. "he iris is different for any two individuals even for identical twins@ 4=A is not unique among identical twins. "he process of capturing the iris image is not intrusive. Iris images can be computer matched more accurately than a face image, and it$s ac nowledged that iris recognition is more accurate than any other biometric technique, although there are some concerns regarding enrollment failure rates ?capturing the initial iris image to be used as a template for comparing with other images>. "he failure to enroll rate ?%"E> is the rate at which a biometric system fails to enroll a sub(ect$s biometric sample. "he process of enrolling a sub(ect for the first time requires some training. "hese are some of the reasons that ma e the iris recognition technology suitable for applications in which the user is cooperative.
.2 -3isting 4or5s
9
Automation System for Students’ Attendance using IRIS Recognition System
• #rea through wor to create the iris1recognition algorithms required for image acquisition and one1to1many matching was pioneered by Aohn ;. 4augman$s, Bh4, 6#E ?Cniversity of Cambridge Computer 9aboratory>. "hese were utili!ed to effectively debut commerciali!ation of the technology in con(unction with an early version of the Iris Access system designed and manufactured by DoreaEs 9; Electronics. 4augmanEs algorithms are the basis of almost all currently ?as of ,--F> commercially deployed iris1recognition systems. In tests where the matching thresholds areGfor better comparabilityGchanged from their default settings to allow a false1accept rate in the region of 1- H7 to 1-H:, the Iris Code false1re(ect rates are comparable to the most accurate single1finger fingerprint matchers. • Iris ;uard$s &omeland *ecurity #order Control has been operating an expellee trac ing system in the Cnited Arab Emirates ?CAE> since ,--1, when the CAE launched a national border1crossing security initiative. "oday, all of the CAEEs land, air and sea ports of entry are equipped with systems. All foreign nationals who possess a visa to enter the CAE are processed through iris cameras installed at all primary and auxiliary immigration inspection points. "o date, the system has apprehended over 77-,--- persons re1entering the CAE with fraudulent travel documents. • 6ne of three biometric identification technologies internationally standardi!ed by ICA6 for use in future passports ?the other two are fingerprint and face recognition> • Iris recognition technology has been implemented by #ioI4 "echnologies *A in Ba istan for C=&C) repatriation pro(ect to control aid distribution for Afghan refugees. )efugees are repatriated by C=&C) in cooperation with ;overnment of Ba istan, and they are paid for their travel. "o ma e sure people do not get paid more than once, their irises are scanned, and the system will detect the refugees on next attempt. "he database has more than 1.7 million iris code templates and around :--- registrations per day. "he one1to1many iris comparison ta es place within 1.< seconds against 1.7 million iris codes.
. Iris Recognition vers$s Other Biometric Technologies
10
Automation System for Students’ Attendance using IRIS Recognition System
"hree factors can be used for security0 something you now ?password or BI=>,
something you have ?smart to en or access card>, and something you are ?biometric>. #iometrics can be used alone or in con(unction with one of the other factors to strengthen the security chec . #iometric technology has advantages over both of the other factors in that the user does not need to remember anything or possess a physical to en in order to be identified. "o ens and cards can be lost, and passwords and BI=s can be forgotten or compromised. A biometric is only susceptible to forgery, which can be extremely difficult, depending on the biometric. Iris recognition falls into the physical biometric category as opposed to behavioral biometrics such as signatures. 6ther physical biometric technologies include fingerprinting, retinal scanning, spea er recognition, and facial scanning and hand geometry. "he =ational Center for *tate Courts ?=C*C> published information comparing these physical biometric methods.,- "he =C*C data is substantiated by a similar comparison table found at the IEEE Computer *ociety.,1 &ere are some highlights from both groups$ findings. &inger(rinting Iris recognition shares many characteristics with fingerprinting. #oth biometric technologies are reliable and very accurate, but iris recognition has a much lower error rate ?1 in 171,---> than fingerprinting ?1 in <--I>.,, ?"he =C*C defines error rate as the crossing point of the graphs of false positives and false negatives of a particular biometric.> #oth biometric methods can be used to verify that a person is who he or she claims to be and to identify a person by comparing the current biometric input to a large set of data that was previously recorded. According to the =C*C, false positives and false negatives are difficult to produce for both fingerprinting and iris recognition.,7 %alse acceptance rates are extremely low for iris recognition. "ests conducted through 4ecember ,--- had not resulted in a single false acceptance of an iris.,: #oth fingerprints and iris are stable physical characteristics that do not change with age. &owever, since older people tend to have drier s in, fingerprints can be more difficult to verify as a person ages. %ingerprinting hardware is generally less expensive than that for iris recognition, but recent technology is lowering costs of iris recognition devices.,< External factors can cause errors in both fingerprinting and iris recognition. %ingerprints can be affected by dirt, dryness and scarring. Iris recognition can be affected by lighting. #oth technologies are
11
Automation System for Students’ Attendance using IRIS Recognition System
reasonably well accepted by the user population, but fingerprinting was rated more intrusive than iris scanning.,J "his rating may be due to the requirement to ma e physical contact with a fingerprinting device. %ingerprinting may also carry some negative connotations due to its historical use in criminal investigations. "here are some health related advantages of iris recognition over fingerprinting. %ingerprinting requires physically touching a device each time the finger is presented for verification. In contrast, the iris template is created without any physical contact with the person whose iris is encoded. "he iris recognition process is, therefore, more appealing to those concerned with hygiene than is fingerprinting. %orgery is not as much of a ris with iris recognition as with fingerprinting. Although sophisticated fingerprinting technology is designed to detect false fingers, a person$s finger can be cut off or used for a mold much easier than an eyeball could be extracted and used for impersonation. In fact, the iris from a person$s extracted eye would not be usable for more than a few seconds.,K Iris recognition devices can also detect the dilating pupil to ensure that the eye is live. Retin"l .c"nning )etinal scanning is often confused with iris recognition, but they are very different biometric technologies. "he retina is located at the bac of the eye and contains distinctive vascular patterns that can be used for identification and verification. )etinal scanning is the only biometric that is more reliable than iris recognition. "he error rate for retinal scanning is 101-,---,--- compared to the iris recognition error rate of 10171,---. ,/ "he retinal scanning process is different from iris recognition and does not involve an IrisCode. #oth retinal and iris technologies are extremely accurate and reliable and have very low false acceptance rates. 6pinions seem to differ on which feature, iris or retina, is more reliable to use throughout life. According to Aohn 5arshall of )etinal "echnologies, L"he iris is harder to map as an image because it fluctuates based on the si!e of the pupil, and drug or medicinal use, and age. "he retina stays constant throughout your life, unless you have glaucoma or diabetes.M,F "rue, the iris is not fully shaped until about eight months of age, but after that age, it is commonly believed to be stable.
12
Automation System for Students’ Attendance using IRIS Recognition System
As depicted in the movie, L5inority )eport,M retinal scanning is a much more intrusive process than iris recognition. A retinal scanning sub(ect must stay very still, with the eye at a distance of no more than 7 inches from the scanner, whereas iris recognition can be accomplished with the sub(ect at a distance of up to about , feet from the camera. Beople wearing glasses must remove them for a retinal scan. %or iris recognition, the =ational Bhysical 9aboratory ?=B9> tests found that glasses can ma e enrollment more difficult, but they can remain in place for verification without causing difficulty.7- "he =B9 tests revealed difficulty in enrolling a blind person$s iris because the system required both eyes to be enrolled.71 4epending upon the nature of the blindness, enrollment of two eyes using retinal scanning might also be prohibitive. =o =B9 data was reported for retinal scans of blind eyes. =either technology has been inexpensive in the past, but recent developments are bringing prices down for both iris recognition and retinal scanning. )etinal scans are probably most appropriate for applications that require the highest levels of security, where the sub(ect is very cooperative and patient, or is required by law to succumb to the scan. .(e"5er Recognition 6f the physical biometric technologies discussed in the =C*C comparison, spea er recognition ran s highest in user acceptance, and is easier to use and less expensive than iris recognition. 3ith an error rate of 1 in <-, spea er recognition is much less accurate than iris recognition.7, false negatives are easy to produce, and the errors can occur due to noise and colds. *pea er recognition could be used to verify a person$s identity, comparing to a previously stored template for a person, but is not recommended for identification. Iris recognition is recommended for both verification and identification.77 &"ci"l Recognition *imilar to iris recognition, facial recognition requires a sub(ect to present his or her face to a camera. #oth technologies are non1intrusive, but they differ in that the sub(ects in facial recognition need not now their identity is being captured on camera. "his aspect can be beneficial in areas where it is important to confirm identity without the sub(ect$s nowledge, but the anonymity with which a facial image can be captured also raises a privacy issue that is not
13
Automation System for Students’ Attendance using IRIS Recognition System
present with iris recognition. Iris recognition is more reliable than facial recognition.7: "he =B9 study cites a false accept rate of 101-- for facial recognition versus 101., million for iris recognition. #"n* 1eometry "he =C*C chart lists hand geometry as one of the easier to use biometric technologies, but it is not as accurate as either iris recognition or retinal scanning. "he error rate for hand geometry is 1 in <-- compared to 1 in 171,--- for iris recognition. Another drawbac of hand geometry technology is that it is relatively easy to produce a false negative, since hand features are not distinctive. "herefore, the technology is not well suited for identification. It should wor well enough for verification as long as the device can recogni!e a fa e hand. Cnli e the iris, hand characteristics could change over time due to scars and growth patterns. &and geometry has the same hygiene issue as fingerprinting.
14
Automation System for Students’ Attendance using IRIS Recognition System
Chapter :
6IT-R!TUR- .UR7-8
15
Automation System for Students’ Attendance using IRIS Recognition System Expanding horizon
/.1 Rese"rch of 7"rio$s !$thors%
,. D"$gm"n. #ow iris recognition wor5s. +rocee*ings of 2992 Intern"tion"l Conference on Im"ge +rocessing) 7ol. 1) 2992. Algorithms developed by the author for recogni!ing persons by their iris patterns have been tested wherein they deal in combinatorial complexity of phase information across different persons who spans about ,:F degrees of freedom and generates discrimination entropy of about 7., bits+mm, over the iris, enabling real1time decisions about personal identity with extremely high confidence. "he high confidence levels are important because they allow very large databases to be searched exhaustively ?one1to1many identification mode.> without ma ing false matches, despite so many chances. C. Tisse) 6. 2"rtin) 6. Torres) 2. Robert. +erson i*entific"tion techni:$e $sing h$m"n iris recognition. Intern"tion"l Conference on 7ision Interf"ce) C"n"*") 2992. "his paper examines a new iris recognition system that implements ?I> gradient decomposed &ough transform + integral1differential operators combination for iris locali!ation and ?II> the Lanalytic imageM concept ?,4 &ilbert transform> to extract pertinent information from iris texture. All these image1processing algorithms have been validated on noised real iris
16
Automation System for Students’ Attendance using IRIS Recognition System
images database. "he proposed innovative technique is computationally effective as well as reliable in terms of recognition rates. 4. 0ong) D. ;h"ng. !cc$r"te iris segment"tion b"se* on novel reflection "n* eyel"sh *etection mo*el. +rocee*ings of 2991 Intern"tion"l .ym(osi$m on Intelligent 2$ltime*i") 7i*eo "n* .(eech +rocessing) #ong 0ong) 2991. In this paper, a novel noise detection model is proposed for accurate segmentation of an iris. Eyelash, eyelid and reflection are three main noises. Eyelid had been solved by traditional eye model@ however, eyelash and reflection are not been regarded. "o determinate a pixel in an eyelash, their model follows the three criterions0 1> separable eyelash condition, ,> non1 informative condition and 7> connective criterion. "he first and second condition handles separable and multiple eyelashes respectively. "he last criterion avoids misclassification of strong iris texture as a single and separable eyelash. %or reflection, a threshold detects strong reflection points and the wea reflection points around the strong points are determined by connective criterion and statistical test. 6. 2") 8. 4"ng) T. T"n. Iris recognition $sing circ$l"r symmetric filters N"tion"l 6"bor"tory of +"ttern Recognition) Instit$te of !$tom"tion) Chinese !c"*emy of .ciences) 2992. &ere the authors deal in a ban of circular symmetric filter is used to capture local iris characteristics to from a fix length feature vector for iris recognition. +. B$rt) -. !*el son. The l"(l"ci"n (yr"mi* "s " com("ct im"ge co*e. I--- Tr"ns"ctions on Comm$nic"tions) 7ol. CO2< 1) No. /) 1=> "hey describe a technique for image encoding in which local operators of many scales but identical shape serve as the basis functions. "he representation differs from established techniques in that the code elements are locali!ed in spatial frequency as well as in space. C. #. D"o$5) 6. !. -l<-sber) &. D. 0"mmo$n "n* 2. !. !l !l"o$i) Iris Recognition) I--I..+IT 2992) 2"rr"5esh.
17
Automation System for Students’ Attendance using IRIS Recognition System
In this paper, a novel technique is developed to create an Iris )ecognition *ystem. "hey deal in a fusion mechanism that amalgamates both, a Canny Edge 4etection scheme and a Circular &ough "ransform, to detect the iris$ boundaries in the eye$s digital image. "his is followed by the application of the &aar wavelet in order to extract the deterministic patterns in a person$s iris in the form of a feature vector. #y comparing the quanti!ed vectors using the &amming 4istance operator, we determine finally whether two irises are similar. T. 6ee. Im"ge re(resent"tion $sing 2D 1"bor w"velets. I--- Tr"ns"ctions of +"ttern !n"lysis "n* 2"chine Intelligence) 7ol. 1>) No. 19) 1==?. "his paper extends to two dimensions the frame criterion developed by 4aubechies for one1dimensional wavelets, and it computes the frame bounds for the particular case of ,4 ;abor wavelets. D. &iel*. Rel"tions between the st"tistics of n"t$r"l im"ges "n* the res(onse. +ro(erties of cortic"l cells. ,o$rn"l of the O(tic"l .ociety of !meric") 1=>@. =atural images are not random@ instead, they exhibit statistical regularities. Assuming that our vision is designed for tas s on natural images, computation in the visual system should be optimi!ed for such regularities. )ecent theoretical investigations along this line have provided many insights into the visual response properties in the early visual system. In this article we review both the nown statistical regularities of natural images, the extent to which low1level vision might be adapted to them, and the recent development in theoretical models to explain this relationship.
/.2 2etho* Use* &or Im(lement"tion%
/.2.1 -*ge Detection Edge detection is a well1developed field on its own within image processing. )egion boundaries and edges are closely related, since there is often a sharp ad(ustment in intensity at the region boundaries. Edge detection techniques have therefore been used as the base of another segmentation technique. "he edges identified by edge detection are often disconnected. "o segment an ob(ect from an image however, one needs closed region boundaries.
/.2.2 .egment"tion
18
Automation System for Students’ Attendance using IRIS Recognition System
In computer vision, segment"tion refers to the process of partitioning a digital image into multiple segments ?sets of pixels, also nown as super pixels>. "he goal of segmentation is to simplify and+or change the representation of an image into something that is more meaningful and easier to analy!e. Image segmentation is typically used to locate ob(ects and boundaries ?lines, curves, etc.> in images. 5ore precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. "he result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image ?li e edge detection>. Each of the pixels in a region is similar with respect to some characteristic or computed property, such as color, intensity, or texture. Ad(acent regions are significantly different with respect to the same characteristic?s>.
/.2. 2e*i"n &ilter In signal processing, it is often desirable to be able to perform some ind of noise reduction on an image or signal. "he me*i"n filter is a nonlinear digital filtering technique, often used to remove noise. *uch noise reduction is a typical pre1processing step to improve the results of later processing ?for example, edge detection on an image>. 5edian filtering is very widely used in digital image processing because under certain conditions, it preserves edges whilst removing noise. "he main idea of the median filter is to run through the signal entry by entry, replacing each entry with the median of neighboring entries. "he pattern of neighbors is called the NwindowN, which slides, entry by entry, over the entire signal. %or 14 signal, the most obvious window is (ust the first few preceding and following entries, whereas for ,4 ?or higher1 dimensional> signals such as images, more complex window patterns are possible ?such as NboxN or NcrossN patterns>. =ote that if the window has an odd number of entries, then the median is simple to define0 it is (ust the middle value after all the entries in the window are sorted numerically. %or an even number of entries, there is more than one possible median. /.2./ Thinning
19
Automation System for Students’ Attendance using IRIS Recognition System
6ptical scanning of the roc inscription yields an image ?file of pixels> that forms the raw input to the 6ptical Character )ecognition *ystem. "he output is the set of recogni!ed characters. Breprocessing is the first phase of document analysis. "he purpose of preprocessing is to improve the quality of the image being processed. It ma es the subsequent phases of image processing li e recognition of characters easier. Thinning is one of the preprocessing methods. In thinning, the image regions are reduced to one1pixel width characters. "hinning is an image preprocessing operation performed to ma e the image crisper by reducing the binary1valued image regions to lines that approximate the s eletons of the region. "hinning cleans the image so that only reduced amount of data needs to be processed in the next image processing stage. *hape analysis could be done easily. "hinning algorithms should perform thinning effectively by successive deletion of dar points ?i.e. changing them to white points> along the edges of the pattern until it is thinned to a line. An effective thinning algorithm is one that can ideally compress data, eliminate local noise without introducing distortions of its own. #ut the ey goal is to retain significant features of the pattern. "here are two types of thinning algorithms 1. *equential thinning algorithms ,. Barallel thinning algorithms In O1P, result of nth iteration depends on result of ?n11>th iteration as well as pixels already processed in the nth iteration. In O,P, deletion of pixels in of nth iteration depends only on the result that remains after ?n11>th iteration. 3e consider only the type O,P algorithms here.
20
Automation System for Students’ Attendance using IRIS Recognition System
Chapter <
R-AUIR-2-NT .+-CI&IC!TION
21
Automation System for Students’ Attendance using IRIS Recognition System
All that system needs
B.1 &$nction"lity Re:$irements
"he system is built to ease the management of students$ attendance. In($t% "he input given to the system will be the eye images of the student. Beh"vior% "he iris is extracted from the eye image and its iris code is generated. "his iris code is compared with those in the database. O$t($t% If iris pattern matched, mar the attendance of that student.
22
Automation System for Students’ Attendance using IRIS Recognition System B.2 #"r*w"re !n* .oftw"re Re:$irements
#"r*w"re Re:$irements 1. 5inimum0 1.J ;&! CBC, <1, 5# )A5, 1-,:xKJ/ display, <:-- )B5 hard dis . ,. )ecommended0 ,., ;&! or higher CBC, 1-,: 5# or more )A5, 1,/-x1-,: display, K,-- )B5 or higher hard dis . 7. 4igital Camera with minimum resolution of < mega pixels. .oftw"re Re:$irements 1. *89 *erver ,--< ,. "urbo C+CII 7. .=E" %ramewor 7.< Qersion number 1 :<-J.7-
B. +rogr"mming -nvironment Re:$irements
.$((orte* D"t"b"ses 1. CA*IA ?Chinese Academy of *ciences 4atabases> ,. #A"& ?Broduced #y Cniversity of #ath> 7. C#I)I* .$((orte* O(er"ting .ystems 1. 5icrosoft 3indows RB ,. 5icrosoft 3indows Qista 6"ng$"ges
23
Automation System for Students’ Attendance using IRIS Recognition System
1. CS 7.< ,. C 7. CII
Chapter J
+RO,-CT +6!NNIN1
24
Automation System for Students’ Attendance using IRIS Recognition System
Laying the foundation
?.1 !ctivity +l"n
.che*$ling 1C Re:$irement 1"thering
.r. No.
N"me of .$b mo*$le
No. of ho$rs
&rom D"te
To D"te
25
Automation System for Students’ Attendance using IRIS Recognition System
1 2 6iter"t$re .$rvey .t$*y of !lgorithm D-3isting IrisC 2C Re:$irement !n"lysis .r. No. 1 2 N"me of .$b mo*$le .co(e Definition &e"sibility .t$*y No. of ho$rs 9= 19 &rom D"te >th .e(tember)9= Bth .e(tember)9= To D"te 1/th .e(tember) 9= 19th .e(tember) 9= 9 /> 1>th !$g$st) 9= 2>th !$g$st) 9= 9th!$g$st) 9= 1Bth .e(tember) 9=
C .ystem Design
.r. No. 1 2
N"me of .$b mo*$le .t$*y of !lgorithms Im(lement"tion of !lgorithms Design of 1UIEs .t$*y of Connectivity Testing the system on *ifferent im"ge form"t
No. of ho$rs 9= 129
&rom D"te 1=th .e(tember) 9= 1>th December) 9=
To D"te 11th October) 9= 2Bth ,"n$"ry) 19
>9 B
12th &ebr$"ry)19 1st 2"rch)19
2>th &ebr$"ry)19 >th 2"rch)19
/
B
/9
12th 2"rch)19
2>th 2"rch)19
? @
Other !s(ects U26 Design
9 9=
1Bth &ebr$"ry) 19 ?th ,"n$"ry) 19
1Bth 2"rch) 19 9th ,"n$"ry) 19
/C .oftw"re Testing
26
Automation System for Students’ Attendance using IRIS Recognition System
Chapter K
D-.I1N
27
Automation System for Students’ Attendance using IRIS Recognition System
Expressing ideas
@.1 Design Overview
Bloc5 Di"gr"m
28
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @.2.1 Bloc5 Di"gr"m
@.2 U26 Di"gr"ms @.2.1 Use C"se Di"gr"m
29
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. .1 Use C"se Di"gr"m
@.2.2 .e:$ence Di"gr"m
30
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. .2 .e:$ence Di"gr"m
@.2. Comm$nic"tion Di"gr"m
31
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re @. ./ Comm$nic"tion Di"gr"m
@.2./ De(loyment Di"gr"m
&ig$re @. .B De(loyment Di"gr"m
32
Automation System for Students’ Attendance using IRIS Recognition System
Chapter /
#O4 .8.T-2 4OR0.
ay it goes!
33
Automation System for Students’ Attendance using IRIS Recognition System >.1 .ystem Overview
"he entire system wor s (ust li e any other application using navigation controls. "he end user can navigate from one page to another and can view image and other details of the entered roll number as he wishes. "he application spans the following pages in accordance with the end user selection0 1. ,. 7. 3elcome Bage *election of the required tas 2 register+recognition If register is selected 7.1 %ill the details of the student 7., Capture his image 7.7 ;enerate the iris code and store in database :. If recognition is selected :.1 Enter the roll number to be verified. :., Capture the image :.7 ;enerate the iris code and compare with the database :.: If verified 2 mar the attendance :.< Else as him to register. <. Qiew the attendance sheet of the whole class. >.1.1 Registering " st$*ent Initially the database of the students has to be prepared, for this purpose the students have to register themselves.
34
Automation System for Students’ Attendance using IRIS Recognition System
"he steps for registering a student are 2 1. ;o to &ome page Computer 4epartment )egister. ,. %ill the details of that student including his =ame, )oll number, 'ear, #ranch, Contact number, Address, E1mail id.
7. "a e the eye image of the student with the specified camera. :. #rowse the photo of the student whose information is filled. <. Bress LCreate irisM. J. "he iris code will be generated. K. Bress the L*ubmitM button. "hus the iris code will be generated for the eye image of that student and will be stored with his personal information.
35
Automation System for Students’ Attendance using IRIS Recognition System
>.1.2 RecogniFing " st$*ent %or recogni!ing a student for mar ing his attendance 2 1. ;o to &ome page Computer 4epartment )ecognition. ,. Enter the roll number of the student you want to recogni!e.
7. Bress L)ecognitionM.
36
Automation System for Students’ Attendance using IRIS Recognition System
:. "he student information will be displayed. <. Bress L#rowseM to select the recent image of the student. J. Bress LCreate irisM. K. "he iris code will be generated. /. Bress LverifyM. F. According to the, the result will be displayed. 1-. If the image is already stored, then is shows LQalid *tudent. Attendance mar ed.M If not, then it as s to L)egisterM.
37
Automation System for Students’ Attendance using IRIS Recognition System
>.2 4or5ing of the system
>.2.1 6ogin +"ge "he welcome page consists of various tabs that allow a user to navigate through the website. "he user can view the contents of the various tabs provided. "he user can enter to the student attendance system using the tab in LComputer 4epartmentM. >.2.2 .election of the re:$ire* t"s5 ' registerGrecognition Bage =ame 0 3elcome Computer 4epartment Input 6utput >.2. 0 Clic on )egister+ )ecognition 0 )egister+)ecognition Bage .electing " (ro(er ste(%
38
Automation System for Students’ Attendance using IRIS Recognition System
>.2. .1 If register is selecte* < %ill the details of the student Bage =ame0 3elcome Computer 4epartment )egister Input 0 )oll no., =ame, Address, Contact, E1mail id, 'ear. >.2. .2 C"(t$re his im"ge Bage =ame0 3elcome Computer 4epartment )egister Input 6utput 0 Eye image. 0 )egister =ew Cser window appears.
>.2. . 1ener"te the iris co*e "n* store in *"t"b"se Bage =ame0 3elcome Computer 4epartment )egister Input 6utput >.2./ 0 Clic on )egister 0 Iris code is generated and information is stored in the database. Reselection of .te(1 >.2./.1 If recognition is selecte* < Enter the roll number to be verified. Bage =ame0 3elcome Computer 4epartment )egister Input 6utput 0 #utton clic to select recognition of the specified roll number. 0 Bage with details of the student.
>.2./.2 C"(t$re the im"ge Capture the image of the student using the digital camera as specified.
39
Automation System for Students’ Attendance using IRIS Recognition System
>.2./. 1ener"te the iris co*e "n* com("re with the *"t"b"se Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 *elect on the current image ta en and clic o . 0 Iris code for the new image is generated and is compared with the database.
>.2././ If verifie* ' m"r5 the "tten*"nce Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 Image for recognition. 0 Qerified and attendance mar ed.
>.2./.B -lse "s5 him to register. Bage =ame0 3elcome Computer 4epartment )ecognition Input 6utput 0 Image for recognition. 0 =ot verified. )egister if not present in the database.
>.2.B 7iew the "tten*"nce sheet of the whole cl"ss. Bage =ame0 3elcome Computer 4epartment )ecognition Attendance *heet Input 6utput 0 Clic on 3elcome Computer 4epartment )ecognition Attendance *heet 0 Attendance *heet for whole class is appearing.
>. .o$rce co*e 2o*$les%
IC .egment"tion
40
Automation System for Students’ Attendance using IRIS Recognition System
+T %unction name 0 segmentUimage?> input output 0 17T17 bloc of the input image in an array form 0 "he entire bloc flagged to be used for further calculations or left to be neglected further. T+ void segmentUimage?> V int iW-,(W-,xW-,yW-,avgW-,countW-@ for?iW-@iX#96CD*@iII> for?(W-@(X#96CD*@(II> V avgW-@ countW-@ for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII> avgWimageOxPOyPIavg@ avgWavg+?3I=T3I=>@ for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII>
41
Automation System for Students’ Attendance using IRIS Recognition System
V if??imageOxPOyPY?avg11->>ZZ?imageOxPOyPX?avgI1->>> countII@ [ if?countY1,1> V for?xW?iT3I=>@xX?iT3I=>I3I=@xII> for?yW?(T3I=>@yX?(T3I=>I3I=@yII> imageOxPOyPW,<<@ [ [ [
IIC Bin"rise Im"ge +T %unction name 0 binariseUimage input 0 17T17 bloc of the image array
4escription 0 Each pixel is either mar ed as - or ,<< depending upon its intensity output 0 17T17 array with each value either as - or ,<<
42
Automation System for Students’ Attendance using IRIS Recognition System
T+ void binariseUimage?> V int iW-,(W-,xW-,yW-,midUvalueW-,upperUboundW-@ for?iW-@iX#96CD*@iII> for?(W-@(X#96CD*@(II> V for?xWiT3I=@xX?iT3I=>I3I=@xII> for?yW(T3I=@yX?(T3I=>I3I=@yII> V numOupperUboundPWimageOxPOyP@ upperUboundII@ [ midUvalueWsort?upperUbound>@ for?xWiT3I=@xX?iT3I=>I3I=@xII> for?yW(T3I=@yX?(T3I=>I3I=@yII> V if?imageOxPOyPXmidUvalue> imageOxPOyPW-@
43
Automation System for Students’ Attendance using IRIS Recognition System
else imageOxPOyPW,<<@ [ midUvalueW-@ upperUboundW-@ [ [
IIIC 2e*i"n &ilter +T %unction name 0 medianUfilter?> input output T+ void medianUfilter?> V int xW-,yW-,midUvalueW-,upperUboundW-@ for?xW1@xX7--@xII> for?yW1@yX7--@yII> V upperUboundW-@
44
0 17 T 17 bloc array of the input image array 0 17 T 17 bloc array with noise eliminated using median filtering
Automation System for Students’ Attendance using IRIS Recognition System
numOupperUboundPWimageOx11POy11P@ numOupperUboundIIPWimageOx11POyP@ numOupperUboundIIPWimageOx11POyI1P@ numOupperUboundIIPWimageOxPOy11P@ numOupperUboundIIPWimageOxPOyP@ numOupperUboundIIPWimageOxPOyI1P@ numOupperUboundIIPWimageOxI1POy11P@ numOupperUboundIIPWimageOxI1POyP@ numOupperUboundIIPWimageOxI1POyI1P@ upperUboundII@ midUvalueWsort?upperUbound>@ imageOxPOyPWmidUvalue@ [ [
45
Automation System for Students’ Attendance using IRIS Recognition System
Chapter F
46
Automation System for Students’ Attendance using IRIS Recognition System
T-.TIN1
Learning from mistakes
=.1 .oftw"re Testing
*oftware "esting is an empirical investigation conducted to provide sta eholders with information about the quality of the product or service under test, with respect to the context in which it is intended to operate. "his includes, but is not limited to, the process of executing a program or application with the intent of finding software bugs. It can also be stated as the process of validating and verifying that a software program+application+product meets the business and technical requirements that guided its design and development, so that it wor s as expected and can be implemented with the same characteristics.
47
Automation System for Students’ Attendance using IRIS Recognition System =.2 Testing "rtif"cts
*oftware testing process can produce several artifacts Test c"se A test case in software engineering normally consists of a unique identifier, requirement references from a design specification, preconditions, events, a series of steps ?also nown as actions> to follow, input, output, expected result, and actual result. Clinically defined a test case is an input and an expected result. "his can be as pragmatic as Efor condition x your derived result is yE, whereas other test cases described in more detail the input scenario and what results might be expected. Test scri(t "he test script is the combination of a test case, test procedure, and test data. Initially the term was derived from the product of wor created by automated regression test tools. "oday, test scripts can be manual, automated, or a combination of both. Test *"t" "he most common test manually or in automation is retesting and regression testing. In most cases, multiple sets of values or data are used to test the same functionality of a particular feature. All the test values and changeable environmental components are collected in separate files and stored as test data. It is also useful to provide this data to the client and with the product or a pro(ect. Test s$ite "he most common term for a collection of test cases is a test suite. "he test suite often also contains more detailed instructions or goals for each collection of test cases. It definitely contains a section where the tester identifies the system configuration used during testing. A group of test cases may also contain prerequisite states or steps, and descriptions of the following tests. Test (l"n
48
Automation System for Students’ Attendance using IRIS Recognition System
A test specification is called a test plan. "he developers are well aware what test plans will be executed and this information is made available to the developers. "his ma es the developers more cautious when developing their code. "his ensures that the developer$s code is not passed through any surprise test case or test plans. Test h"rness "he software, tools, samples of data input and output, and configurations are all referred to collectively as a test harness.
=. .ystem ($t to Test =. .1 Testing .n"(shots
49
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1.1 Test C"ses.
50
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1.2 R$n Test.
51
Automation System for Students’ Attendance using IRIS Recognition System
&ig$re =. .1. 7"li*"tion Test.
=. .2 Testing Re(ort
52
Automation System for Students’ Attendance using IRIS Recognition System
.$bject 1 Browsing thro$gh the website 1.1 !$thentic"tion .$bject% 9ogin .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 1.1.1 *teps .te( N"me Descri(tion -3(ecte* Res$lt *tep 1 #rowsing through the web 3hen the web site name is pages. given in the address bar the home page is opened. *tep , Clic ing on About 5AE tab. 3hen clic ed on NAbout 5AEN "ab home page is displayed. *tep 7 Clic ing on Infrastructure tab. 3hen clic ed on N InfrastructureN "ab Infrastructure page is opened. *tep : Clic ing on Blacement Cell 3hen clic ed on N Blacement tab. CellN "ab Blacement Cell page is opened. *tep < Clic ing on Contact Cs tab. 3hen clic ed on N Contact CsN "ab Contact Cs page is opened. *tep J *tep K Clic ing on department Computer 3hen clic ed on N Computer departmentN "ab "wo sub parts are opened. Chec the feed bac in the %eed bac is accepted in the web page. web page.
1.2 Register New .t$*ent .$bject% 9ogin .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 1.,.1 *teps .te( N"me Descri(tion *tep 1 Entering )oll =umber student. *tep , Entering =ame of student.
53
-3(ecte* Res$lt of 6nly numbers are accepted, characters are not allowed. Characters are allowed.
Automation System for Students’ Attendance using IRIS Recognition System
*tep 7 Entering E1mail id of student. 6nly the E1mail ids accrding to 4=* system are accepted otherwise displays the error msg. Entering Address of student . "he address of the student is accepted. Entering Contact no of the 6nly =umbers can be entered. student.
*tep : *tep <
2 .chem" Det"ils 2.1 +roce*$res .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.1.1 *teps .te( N"me Descri(tion *tep 1 Bress browse in the registration web page. *tep , *elect particular eye image of the respective student. *tep 7 Bress create iris code. *tep : Bress submit.
-3(ecte* Res$lt "he dialog box for choosing the image is displayed. "he eye image is displayed. "he processing of selected eye image ta es place and iris code is generated. "he generated iris code along with the entered information of the student is inserted into the database.
2.2 Recognition of " st$*ent .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.7.1 *teps .te( N"me Descri(tion -3(ecte* Res$lt *tep 1 Enter the )oll number to be "he entered information of the recognised and pressed give roll number is displayed. recognise.
54
Automation System for Students’ Attendance using IRIS Recognition System
*tep , *tep 7 Bress #rowse. Bress Qerify. "he dialog box for selecting a particular eye image is displayed. "he iris code for the newly given eye image is generated and compared with the already existing entries.
2. 7iew the tot"l "tten*"nce .$bject% *chema4etails .t"t$s% 4esign Designer% admin Cre"tion D"te% ,-+-:+1Ty(e% 5A=CA9 ,.7.1 *teps .te( N"me Descri(tion *tep 1 "est the database. *tep ,
-3(ecte* Res$lt database is opened and attendance sheet is displayed. Qiew the present status of the Bresent *tatus of the student is student. displayed.
55
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 1-
CONC6U.ION
Leap towards the new "eginning
"he system for attendance management wor s efficiently for various types of image such as .bmp, .(peg, and other formats. "his system is also built up to show the total attendance of the students. As a website, this system can be uploaded on the internet and can be viewed as a website. "hus, in total this system can be described as1 !$tom"te* 2 As it successfully monitors the attendance.
56
Automation System for Students’ Attendance using IRIS Recognition System
.ec$re* 2 #uilt in A*B.=et ma es it secured website. &le3ible 2 As it can run on different image format. A$ic5 2 As the response time of the system is very less.
57
Automation System for Students’ Attendance using IRIS Recognition System
Chapter 11
&UTUR- .CO+-
Thinking out of the "ox
3e have wor ed sufficiently on still images for iris recognition of a person and applied it for managing the attendance. "his concept of iris recognition for still images can be further extended to 1 1. Iris recognition using a real time video. ,. #uilt a complete product to ma e it as fully fledged software. 7. "he developed application should be able to support a large database. :. "he response time for the system supporting large database should be very less.
58
Automation System for Students’ Attendance using IRIS Recognition System
At last, the unique biometric identification technique of I)I* recognition should be applicable to a variety of real time systems for Qerification, Identification, *ecurity and *afety purposes.
59
