26 August 2016 Enhanced retinal modeling for face recognition and facial feature point detection under complex illumination conditions
Author Affiliations +
Abstract
We improved classic retinal modeling to alleviate the adverse effect of complex illumination on face recognition and extracted robust image features. Our improvements on classic retinal modeling included three aspects. First, a combined filtering scheme was applied to simulate functions of horizontal and amacrine cells for accurate local illumination estimation. Second, we developed an optimal threshold method for illumination classification. Finally, we proposed an adaptive factor acquisition model based on the arctangent function. Experimental results on the combined Yale B; the Carnegie Mellon University poses, illumination, and expression; and the Labeled Face Parts in the Wild databases show that the proposed method can effectively alleviate illumination difference of images under complex illumination conditions, which is helpful for improving the accuracy of face recognition and that of facial feature point detection.
© 2016 SPIE and IS&T
Yong Cheng, Yong Cheng, Zuoyong Li, Zuoyong Li, Liangbao Jiao, Liangbao Jiao, Hong Lu, Hong Lu, Xuehong Cao, Xuehong Cao, } "Enhanced retinal modeling for face recognition and facial feature point detection under complex illumination conditions," Journal of Electronic Imaging 25(4), 043028 (26 August 2016). https://doi.org/10.1117/1.JEI.25.4.043028 . Submission:
JOURNAL ARTICLE
11 PAGES


SHARE
RELATED CONTENT

Face recognition based tensor structure
Proceedings of SPIE (November 15 2011)
Frontal-view face detection
Proceedings of SPIE (April 20 1995)
Feature based sliding window technique for face recognition
Proceedings of SPIE (February 26 2010)

Back to Top