Open AccessFace Recognition Using Dense SIFT Feature Alignment
Author(s) -
Zhou Quan,
Shafiq ur Rehman,
Zhou Yu,
Wei Xin,
Wang Lei,
Zheng Baoyu
Publication year - 2016
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2016.10.001
Subject(s) - scale invariant feature transform , artificial intelligence , pattern recognition (psychology) , computer science , facial recognition system , benchmark (surveying) , feature (linguistics) , face (sociological concept) , feature matching , invariant (physics) , matching (statistics) , transformation (genetics) , feature extraction , computer vision , mathematics , statistics , social science , linguistics , philosophy , biochemistry , chemistry , geodesy , sociology , mathematical physics , gene , geography
This paper addresses face recognition problem in a more challenging scenario where the training and test samples are both subject to the visual variations of poses, expressions and misalignments. We employ dense Scale‐invariant feature transform (SIFT) feature matching as a generic transformation to roughly align training samples; and then identify input facial images via an improved sparse representation model based on the aligned training samples. Compared with previous methods, the extensive experimental results demonstrate the effectiveness of our method for the task of face recognition on three benchmark datasets.