Abstract
The deep convolutional neural networks for face recognition, from DeepFace to the recent FaceNet, demand a sufficiently large volume of filters for feature extraction, in addition to being deep. The shallow filter-bank approaches, e.g., principal component analysis network (PCANet), binarized statistical image features (BSIF), and other analogous variants, endure the filter scarcity problem that not all PCA and ICA filters available are discriminative to abstract noise-free features. This paper extends our previous work on multi-fold filter convolution (â.,3-FFC), where the pre-learned PCA and ICA filter sets are exponentially diversified by â.,3 folds to instantiate PCA, ICA, and PCA-ICA offspring. The experimental results unveil that the 2-FFC operation solves the filter scarcity state. The 2-FFC descriptors are also evidenced to be superior to that of PCANet, BSIF, and other face descriptors, in terms of rank-1 identification rate (%).
| Original language | English |
|---|---|
| Title of host publication | Second International Workshop on Pattern Recognition |
| Editors | Guojian Chen, Xudong Jiang, Masayuki Arai |
| Publisher | SPIE |
| Volume | 10443 |
| ISBN (Electronic) | 9781510613508 |
| DOIs | |
| Publication status | Published - 2017 Jan 1 |
| Event | 2nd International Workshop on Pattern Recognition, IWPR 2017 - Singapore, Singapore Duration: 2017 May 1 → 2017 May 3 |
Other
| Other | 2nd International Workshop on Pattern Recognition, IWPR 2017 |
|---|---|
| Country | Singapore |
| City | Singapore |
| Period | 17/5/1 → 17/5/3 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Cite this
}
Finessing filter scarcity problem in face recognition via multi-fold filter convolution. / Low, Cheng Yaw; Teoh, Beng Jin.
Second International Workshop on Pattern Recognition. ed. / Guojian Chen; Xudong Jiang; Masayuki Arai. Vol. 10443 SPIE, 2017. 104430G.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Finessing filter scarcity problem in face recognition via multi-fold filter convolution
AU - Low, Cheng Yaw
AU - Teoh, Beng Jin
PY - 2017/1/1
Y1 - 2017/1/1
N2 - The deep convolutional neural networks for face recognition, from DeepFace to the recent FaceNet, demand a sufficiently large volume of filters for feature extraction, in addition to being deep. The shallow filter-bank approaches, e.g., principal component analysis network (PCANet), binarized statistical image features (BSIF), and other analogous variants, endure the filter scarcity problem that not all PCA and ICA filters available are discriminative to abstract noise-free features. This paper extends our previous work on multi-fold filter convolution (â.,3-FFC), where the pre-learned PCA and ICA filter sets are exponentially diversified by â.,3 folds to instantiate PCA, ICA, and PCA-ICA offspring. The experimental results unveil that the 2-FFC operation solves the filter scarcity state. The 2-FFC descriptors are also evidenced to be superior to that of PCANet, BSIF, and other face descriptors, in terms of rank-1 identification rate (%).
AB - The deep convolutional neural networks for face recognition, from DeepFace to the recent FaceNet, demand a sufficiently large volume of filters for feature extraction, in addition to being deep. The shallow filter-bank approaches, e.g., principal component analysis network (PCANet), binarized statistical image features (BSIF), and other analogous variants, endure the filter scarcity problem that not all PCA and ICA filters available are discriminative to abstract noise-free features. This paper extends our previous work on multi-fold filter convolution (â.,3-FFC), where the pre-learned PCA and ICA filter sets are exponentially diversified by â.,3 folds to instantiate PCA, ICA, and PCA-ICA offspring. The experimental results unveil that the 2-FFC operation solves the filter scarcity state. The 2-FFC descriptors are also evidenced to be superior to that of PCANet, BSIF, and other face descriptors, in terms of rank-1 identification rate (%).
UR - http://www.scopus.com/inward/record.url?scp=85028548855&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028548855&partnerID=8YFLogxK
U2 - 10.1117/12.2280352
DO - 10.1117/12.2280352
M3 - Conference contribution
VL - 10443
BT - Second International Workshop on Pattern Recognition
A2 - Chen, Guojian
A2 - Jiang, Xudong
A2 - Arai, Masayuki
PB - SPIE
ER -