Abstract
Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.
| Original language | English |
|---|---|
| Pages (from-to) | 2791-2805 |
| Number of pages | 15 |
| Journal | IEEE Transactions on Image Processing |
| Volume | 27 |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - 2018 Jun 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Graphics and Computer-Aided Design
Cite this
}
An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition. / Oh, Beom Seok; Toh, Kar Ann; Teoh, Beng Jin; Lin, Zhiping.
In: IEEE Transactions on Image Processing, Vol. 27, No. 6, 01.06.2018, p. 2791-2805.Research output: Contribution to journal › Article
TY - JOUR
T1 - An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition
AU - Oh, Beom Seok
AU - Toh, Kar Ann
AU - Teoh, Beng Jin
AU - Lin, Zhiping
PY - 2018/6/1
Y1 - 2018/6/1
N2 - Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.
AB - Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.
UR - http://www.scopus.com/inward/record.url?scp=85042720499&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85042720499&partnerID=8YFLogxK
U2 - 10.1109/TIP.2018.2809040
DO - 10.1109/TIP.2018.2809040
M3 - Article
C2 - 29570082
AN - SCOPUS:85042720499
VL - 27
SP - 2791
EP - 2805
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
SN - 1057-7149
IS - 6
ER -