Proceedings of the 2016 International Conference on Computer Engineering and Information Systems

Metric Learning Based Multi-Patch Ensemble for High Precision Face Verification

Authors
Dang-Dang Chen, Lan-Qing He, Zhong-Dao Wang, Sheng-Jin Wang
Corresponding Author
Dang-Dang Chen
Available Online November 2016.
DOI
https://doi.org/10.2991/ceis-16.2016.32How to use a DOI?
Keywords
face recognition; deep learning; CNN; LFW; metric learning
Abstract
Face verification under video surveillance is an important issue in computer vision for decades. Several methods on automatic face verification have significantly raised the accuracy by using Gabor wavelets, high-dimensional LBP features, Fisher vectors, Joint Bayesian, etc. Especially the usage of Deep Convolution Neural Networks(CNNs), artificial intelligence beats humans for the first time on Labeled Faces in the Wild(LFW) face verification task. In order to further improve the verification accuracy, we propose an approach that combines a multi-patch deep CNN by using two step metric learning. Experiments show that our method archives an accuracy of 99.37% on LFW, and 92.80% on YouTube Faces(YTF), which is very competitive with the state-of-the-art.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2016 International Conference on Computer Engineering and Information Systems
Part of series
Advances in Computer Science Research
Publication Date
November 2016
ISBN
978-94-6252-283-1
ISSN
2352-538X
DOI
https://doi.org/10.2991/ceis-16.2016.32How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Dang-Dang Chen
AU  - Lan-Qing He
AU  - Zhong-Dao Wang
AU  - Sheng-Jin Wang
PY  - 2016/11
DA  - 2016/11
TI  - Metric Learning Based Multi-Patch Ensemble for High Precision Face Verification
BT  - 2016 International Conference on Computer Engineering and Information Systems
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/ceis-16.2016.32
DO  - https://doi.org/10.2991/ceis-16.2016.32
ID  - Chen2016/11
ER  -