Abstract
In this work, we propose a novel technique for face recognition with pose variations in image sequences using a cellular simultaneous recurrent network (CSRN). We formulate the recognition prob lem with such large-pose variations as an implicit temporal prediction task for CSRN. We exploit a face extraction algorithm based on the scale-space method and facial structural knowledge as a preprocessing step. Further, to reduce computational cost, we obtain eigenfaces for a set of image sequences for each person and use these reduced pattern vectors as the input to CSRN. CSRN learns how to associate each face class/person in the training phase. A modified distance metric between successive frames of test and training output pattern vectors indicate either a match or mismatch between the two corresponding face classes. We extensively evaluate our CSRN-based face recognition technique using the publicly available VidTIMIT Audio-Video face dataset. Our simulation shows that for this dataset with large-scale pose variations, we can obtain an overall 77% face recognition rate.
© 2010 Optical Society of America
Full Article | PDF ArticleMore Like This
Ajmal Mian
Opt. Express 19(8) 7491-7506 (2011)
Hwanjong Song, Sangyoun Lee, Jaihie Kim, and Kwanghoon Sohn
Appl. Opt. 44(5) 677-687 (2005)
Shaohua Kevin Zhou and Rama Chellappa
J. Opt. Soc. Am. A 22(2) 217-229 (2005)