Abstract
In this paper, we proposed an optimized Sparse Deep Learning Network (SDLN) model for Face Recognition (FR). A key contribution of this work is to learn feature coding of human face with a SDLN based on local structured Sparse Representation (SR). In traditional sparse FR methods, different poses and expressions of training samples could have great influence on the recognition results. We consider the SR that should be guided by context constraints which are defined by the correlations of dictionary atoms. The over-complete common dictionary that contains common atom set has been learned from a local region structured sparse encoding process. We obtained over-complete common dictionary and feature coding for each face. As we all know that the deep learning has been widely applied to face feature learning. Using traditional deep learning methods can not contain variations of face identity information. We have to get face features of compatible change in a jointly deep learning network. The proposed SDLN is jointly fine-tuned to optimize for the task of FR. The SDLN achieves high FR performance on the ORL and FERET database.
| Original language | English |
|---|---|
| Title of host publication | 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings |
| Publisher | IEEE Computer Society |
| Pages | 3026-3030 |
| Number of pages | 5 |
| Volume | 2016-August |
| ISBN (Electronic) | 9781467399616 |
| DOIs | |
| Publication status | Published - 2016 Aug 3 |
| Event | 23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: 2016 Sep 25 → 2016 Sep 28 |
Other
| Other | 23rd IEEE International Conference on Image Processing, ICIP 2016 |
|---|---|
| Country | United States |
| City | Phoenix |
| Period | 16/9/25 → 16/9/28 |
Fingerprint
Keywords
- Atom decomposition
- Face recognition
- Over-complete dictionary learning
- Restricted boltzmann machine
- Sparse deep learning network
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
A jointly local structured sparse deep learning network for face recognition. / Wu, Renjie; Kamata, Seiichiro.
2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 3026-3030 7532915.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A jointly local structured sparse deep learning network for face recognition
AU - Wu, Renjie
AU - Kamata, Seiichiro
PY - 2016/8/3
Y1 - 2016/8/3
N2 - In this paper, we proposed an optimized Sparse Deep Learning Network (SDLN) model for Face Recognition (FR). A key contribution of this work is to learn feature coding of human face with a SDLN based on local structured Sparse Representation (SR). In traditional sparse FR methods, different poses and expressions of training samples could have great influence on the recognition results. We consider the SR that should be guided by context constraints which are defined by the correlations of dictionary atoms. The over-complete common dictionary that contains common atom set has been learned from a local region structured sparse encoding process. We obtained over-complete common dictionary and feature coding for each face. As we all know that the deep learning has been widely applied to face feature learning. Using traditional deep learning methods can not contain variations of face identity information. We have to get face features of compatible change in a jointly deep learning network. The proposed SDLN is jointly fine-tuned to optimize for the task of FR. The SDLN achieves high FR performance on the ORL and FERET database.
AB - In this paper, we proposed an optimized Sparse Deep Learning Network (SDLN) model for Face Recognition (FR). A key contribution of this work is to learn feature coding of human face with a SDLN based on local structured Sparse Representation (SR). In traditional sparse FR methods, different poses and expressions of training samples could have great influence on the recognition results. We consider the SR that should be guided by context constraints which are defined by the correlations of dictionary atoms. The over-complete common dictionary that contains common atom set has been learned from a local region structured sparse encoding process. We obtained over-complete common dictionary and feature coding for each face. As we all know that the deep learning has been widely applied to face feature learning. Using traditional deep learning methods can not contain variations of face identity information. We have to get face features of compatible change in a jointly deep learning network. The proposed SDLN is jointly fine-tuned to optimize for the task of FR. The SDLN achieves high FR performance on the ORL and FERET database.
KW - Atom decomposition
KW - Face recognition
KW - Over-complete dictionary learning
KW - Restricted boltzmann machine
KW - Sparse deep learning network
UR - http://www.scopus.com/inward/record.url?scp=85006817319&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85006817319&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2016.7532915
DO - 10.1109/ICIP.2016.7532915
M3 - Conference contribution
AN - SCOPUS:85006817319
VL - 2016-August
SP - 3026
EP - 3030
BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PB - IEEE Computer Society
ER -