Abstract
In this paper, we propose a single hidden-layer Gabor-based network for heterogeneous face recognition. The proposed input layer contains novel computational units which propagate geometrically localized input image sub-blocks to hidden nodes. The propagated pixels are then convolved with a set of Gabor kernels followed by a randomly weighted summation and a non-linear activation function operation. The output layer adopts a linear weighting scheme which can be deterministically estimated similar to that in extreme learning machine. Our experiments on three experimental scenarios using BERC visual-thermal infrared database and CASIA visual-near infrared database show promising results for the proposed network.
| Original language | English |
|---|---|
| Pages (from-to) | 253-265 |
| Number of pages | 13 |
| Journal | Neurocomputing |
| Volume | 261 |
| DOIs | |
| Publication status | Published - 2017 Oct 25 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Science Applications
- Cognitive Neuroscience
Cite this
}
A Gabor-based network for heterogeneous face recognition. / Oh, Beom Seok; Oh, Kangrok; Teoh, Andrew Beng Jin; Lin, Zhiping; Toh, Kar Ann.
In: Neurocomputing, Vol. 261, 25.10.2017, p. 253-265.Research output: Contribution to journal › Article
TY - JOUR
T1 - A Gabor-based network for heterogeneous face recognition
AU - Oh, Beom Seok
AU - Oh, Kangrok
AU - Teoh, Andrew Beng Jin
AU - Lin, Zhiping
AU - Toh, Kar Ann
PY - 2017/10/25
Y1 - 2017/10/25
N2 - In this paper, we propose a single hidden-layer Gabor-based network for heterogeneous face recognition. The proposed input layer contains novel computational units which propagate geometrically localized input image sub-blocks to hidden nodes. The propagated pixels are then convolved with a set of Gabor kernels followed by a randomly weighted summation and a non-linear activation function operation. The output layer adopts a linear weighting scheme which can be deterministically estimated similar to that in extreme learning machine. Our experiments on three experimental scenarios using BERC visual-thermal infrared database and CASIA visual-near infrared database show promising results for the proposed network.
AB - In this paper, we propose a single hidden-layer Gabor-based network for heterogeneous face recognition. The proposed input layer contains novel computational units which propagate geometrically localized input image sub-blocks to hidden nodes. The propagated pixels are then convolved with a set of Gabor kernels followed by a randomly weighted summation and a non-linear activation function operation. The output layer adopts a linear weighting scheme which can be deterministically estimated similar to that in extreme learning machine. Our experiments on three experimental scenarios using BERC visual-thermal infrared database and CASIA visual-near infrared database show promising results for the proposed network.
UR - http://www.scopus.com/inward/record.url?scp=85014092835&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85014092835&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2015.11.137
DO - 10.1016/j.neucom.2015.11.137
M3 - Article
AN - SCOPUS:85014092835
VL - 261
SP - 253
EP - 265
JO - Review of Economic Dynamics
JF - Review of Economic Dynamics
SN - 1094-2025
ER -