Welcome to the InfoSci Platform
Reference Hub8
Video Face Tracking and Recognition with Skin Region Extraction and Deformable Template Matching

Video Face Tracking and Recognition with Skin Region Extraction and Deformable Template Matching

Simon Clippingdale, Mahito Fujii
Copyright: © 2012 |Volume: 3 |Issue: 1 |Pages: 13
ISSN: 1947-8534|EISSN: 1947-8542|EISBN13: 9781466613577|DOI: 10.4018/jmdem.2012010103
Cite Article Cite Article

MLA

Clippingdale, Simon, and Mahito Fujii. "Video Face Tracking and Recognition with Skin Region Extraction and Deformable Template Matching." IJMDEM vol.3, no.1 2012: pp.36-48. http://doi.org/10.4018/jmdem.2012010103

APA

Clippingdale, S. & Fujii, M. (2012). Video Face Tracking and Recognition with Skin Region Extraction and Deformable Template Matching. International Journal of Multimedia Data Engineering and Management (IJMDEM), 3(1), 36-48. http://doi.org/10.4018/jmdem.2012010103

Chicago

Clippingdale, Simon, and Mahito Fujii. "Video Face Tracking and Recognition with Skin Region Extraction and Deformable Template Matching," International Journal of Multimedia Data Engineering and Management (IJMDEM) 3, no.1: 36-48. http://doi.org/10.4018/jmdem.2012010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The authors describe a face tracking and recognition system for video indexing that handles variable face poses (left-right and up-down) and deformations due to speech and facial expressions. The system is based on deformable template matching, and employs person-specific templates at near-frontal poses for recognition, and novel person-independent templates at multiple poses on the view-sphere for tracking. Relative to an earlier version that used multiple person-specific templates at multiple (left-right) poses, the new system speeds up processing by (i) restricting attention to skin-color regions; (ii) performing recognition using the person-specific templates at near-frontal poses only; and (iii) tracking at non-frontal poses using the novel person-independent templates. Registration is also simplified since multiple views of each target individual are no longer required, but at the cost of a loss of recognition functionality at poses far from frontal (the system instead “remembers” the identity of each individual from near-frontal matches and tracks between them).

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.