Real Time Tracking of Facial Features

Published on June 2016 | Categories: Documents | Downloads: 42 | Comments: 0 | Views: 176
of 18
Download PDF   Embed   Report

Comments

Content

REAL TIME TRACKING OF FACIAL FEATURES
by
ABHISHEK KUMAR – (REG. NO. 200912004) ASEEM SINHA - (REG. NO. 200912018) PRAVEEN KUMAR - (REG. NO. 200912071)

Under the Guidance ofMRS. AMRITA BISWAS Associate Professor EC Department SMIT

Department of Electronics and Communication Sikkim Manipal Institute of Technology Majitar,Rangpo,East Sikkim-737136

CONTENTS
• • • • • • • • • • Objective Motivation Difficulties Introduction Implementation Results Applications Limitations Conclusion Future scope

OBJECTIVE
• Detection of multiple faces from a still image. • Creating a mask in order to fit on the face. • Detection and features tracking of single face from video. • Detection and features tracking of multiple faces from video.

MOTIVATION
• The wide range of commercial and law enforcement applications. • The availability of feasible technologies for research and projects. • Current systems are still far away from the capability to cope up with real time applications.

DIFFICULTIES
• • • • Face Variation Face position Wearing glasses Low resolution images

INTRODUCTION
• Face detection It is the task of localizing faces in an input image, is a fundamental part of any face processing system. The extracted faces can then be used for initializing face tracking or automatic face recognition.

• Face feature tracking It is the process of locating a moving face or several of them over a period of time and then locating facial features like eyes, nose and mouth.

IMPLEMENTATION

CONTD…

RESULTS
Actual image Processed image

RESULTS CONTD…
Actual video frame Processed video frame

RESULTS CONTD…
Actual video frame Processed video frame

APPLICATIONS
• • • • • Access control Identification systems Biometrics Video surveillance Human computer interface

LIMITATIONS
• Due to bad lighting condition, tracking is sometimes not possible. • Due to partially covered faces, tracking is not possible. • Fully rotated faces are not possible to track.

CONCLUSION
• We proposed a modified method for automatic fitting of a deformable face mask to a previous unseen face. • By making mask we are able to fit this mask to different input images and video. • The face model is built with the high and low image resolution. • Successful implementation on multiple faces.

FUTURE SCOPE
• Work can be done to link the project with database for security purposes. • Further processing can be done for rotated faces. • Further processing can be done for blurred images and videos.

REFERENCES
• P. Viola and M. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features”, vol. 2, pp. 240-249, 2003. • J.G. Wang and E . Sung, “Frontal view detection and facial features extraction using color and morphological operations”, Pattern recognition letters, vol. 20, pp. 1053-1068, oct . 1999. • W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, “Face recognition: A literature survey,” ACM Computing Surveys, vol. 35, no. 4, pp. 399–458, 2003. • Digital Image Processing Using MATLAB by Gonzalez, Woods & Eddins, Prentice, pp.25-29.

THANK YOU!

Sponsor Documents

Or use your account on DocShare.tips

Hide

Forgot your password?

Or register your new account on DocShare.tips

Hide

Lost your password? Please enter your email address. You will receive a link to create a new password.

Back to log-in

Close