DocumentCode :
3320210
Title :
Spatial co-occurrence of local intensity order for face recognition
Author :
Xianbiao Qi ; Yi Lu ; Shifeng Chen ; Chun-Guang Li ; Jun Guo
Author_Institution :
Beijing Univ. of Posts & Telecommun., Beijing, China
fYear :
2013
fDate :
15-19 July 2013
Firstpage :
1
Lastpage :
6
Abstract :
In this paper, we propose a simple but effective spatial co-occurrence of local intensity order (CoLIO) feature for face recognition. Local intensity order (LIO) is robust to illumination variance. Spatial co-occurrence of LIO not only preserves great invariance to illumination, but also greatly enhances the discriminative power of the descriptor as Co- LIO well captures the correlation between locally adjacent regions. The proposed feature has been successfully applied to two widely used face databases including AR [1] and LFW [2]. Superior performance on these two databases fully demonstrates the effectiveness of the proposed feature. Meanwhile, the extremely fast extraction speed makes the proposed feature practically useful.
Keywords :
face recognition; feature extraction; AR; CoLIO; LFW; face databases; face recognition; fast extraction speed; illumination variance; spatial cooccurrence of local intensity order feature; Correlation; Databases; Face; Face recognition; Feature extraction; Lighting; Training; Face Recognition; Local Intensity Order; Spatial Co-occurrence;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo Workshops (ICMEW), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
Type :
conf
DOI :
10.1109/ICMEW.2013.6618447
Filename :
6618447
Link To Document :
بازگشت