TY - JOUR
T1 - Individual stable space: an approach to face recognition under uncontrolled conditions
AU - Geng, Xin
AU - Smith-Miles, Kate Amanda
AU - Zhou, Zhi-Hua
PY - 2008
Y1 - 2008
N2 - There usually exist many kinds of variations in face images taken under uncontrolled conditions, such as changes of pose, illumination, expression, etc. Most previous works on face recognition focus on particular variations and usually assume the absence of others. Instead of such a a??divide and conquera?? strategy, this paper attempts to directly address face recognition under uncontrolled conditions. The key is the Individual Stable Space (ISS) which only expresses personal characteristics. A neural network named ISNN is proposed to map a raw face image into the ISS. After that, three ISS-based algorithms are designed for face recognition under uncontrolled conditions. There are no restrictions for the images fed into these algorithms. Moreover, unlike many other face recognition techniques, they do not require any extra training information, such as the view angle. These advantages make them practical to implement under uncontrolled conditions. The proposed algorithms are tested on three large face databases with vast variations and achieve superior performance compared with other 12 existing face recognition techniques.
AB - There usually exist many kinds of variations in face images taken under uncontrolled conditions, such as changes of pose, illumination, expression, etc. Most previous works on face recognition focus on particular variations and usually assume the absence of others. Instead of such a a??divide and conquera?? strategy, this paper attempts to directly address face recognition under uncontrolled conditions. The key is the Individual Stable Space (ISS) which only expresses personal characteristics. A neural network named ISNN is proposed to map a raw face image into the ISS. After that, three ISS-based algorithms are designed for face recognition under uncontrolled conditions. There are no restrictions for the images fed into these algorithms. Moreover, unlike many other face recognition techniques, they do not require any extra training information, such as the view angle. These advantages make them practical to implement under uncontrolled conditions. The proposed algorithms are tested on three large face databases with vast variations and achieve superior performance compared with other 12 existing face recognition techniques.
UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.2717
U2 - 10.1.1.113.2717
DO - 10.1.1.113.2717
M3 - Article
VL - 19
SP - 1354
EP - 1368
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
SN - 2162-237X
IS - 8
ER -