By Topic

A novel approach for person authentication and content-based tracking in videos using kernel methods and active appearance models

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
N. Kumar ; Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur, India ; V. Abhishek ; G. Gautam

A novel integration of methods for person authentication and tracking is proposed for real time security systems. The implementation of the idea for this real time implementation follows a three step procedure-face detection, recognition and content-based tracking. Instead of analyzing continuous videos we sample the frame based on a method derived from Shannon's information theory model. The Face-detector detects multi-viewed faces in a video using feature-based kernel methods in a reduced feature space obtained using ICA. The identified "face regions" are then passed on to the face recognition system which is based on Active Appearance Models (AAM). Once the subject is recognized, it can be tracked in the video using kernel based object tracking method. Several space reduction techniques have been used like ICA, PCA and skin-color segmentation.

Published in:

Systems, Man and Cybernetics, 2003. IEEE International Conference on  (Volume:2 )

Date of Conference:

5-8 Oct. 2003