21 October 2013 Tracking and recognition face in videos with incremental local sparse representation model
Author Affiliations +
Optical Engineering, 52(10), 103112 (2013). doi:10.1117/1.OE.52.10.103112
Abstract
This paper addresses the problem of tracking and recognizing faces via incremental local sparse representation. First a robust face tracking algorithm is proposed via employing local sparse appearance and covariance pooling method. In the following face recognition stage, with the employment of a novel template update strategy, which combines incremental subspace learning, our recognition algorithm adapts the template to appearance changes and reduces the influence of occlusion and illumination variation. This leads to a robust video-based face tracking and recognition with desirable performance. In the experiments, we test the quality of face recognition in real-world noisy videos on YouTube database, which includes 47 celebrities. Our proposed method produces a high face recognition rate at 95% of all videos. The proposed face tracking and recognition algorithms are also tested on a set of noisy videos under heavy occlusion and illumination variation. The tracking results on challenging benchmark videos demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods. In the case of the challenging dataset in which faces undergo occlusion and illumination variation, and tracking and recognition experiments under significant pose variation on the University of California, San Diego (Honda/UCSD) database, our proposed method also consistently demonstrates a high recognition rate.
© 2013 Society of Photo-Optical Instrumentation Engineers (SPIE)
Chao Wang, Yunhong Wang, Zhaoxiang Zhang, "Tracking and recognition face in videos with incremental local sparse representation model," Optical Engineering 52(10), 103112 (21 October 2013). http://dx.doi.org/10.1117/1.OE.52.10.103112
JOURNAL ARTICLE
14 PAGES


SHARE
KEYWORDS
Facial recognition systems

Video

Detection and tracking algorithms

Databases

Optical tracking

Motion models

Optical engineering

RELATED CONTENT

Multiple-model filtering
Proceedings of SPIE (July 30 1998)
Image partition boundary coding
Proceedings of SPIE (October 01 1998)
Emerging video compression technologies
Proceedings of SPIE (March 22 1996)
Automated adaptation for ATR algorithms
Proceedings of SPIE (June 20 1995)

Back to Top