Joint Feature Learning for Face Recognition

This paper presents a new joint feature learning (JFL) approach to automatically learn feature representation from raw pixels for face recognition. Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for fa...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu, Jiwen, Liong, Venice Erin, Wang, Gang, Moulin, Pierre
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2016
Subjects:
Online Access:https://hdl.handle.net/10356/81670
http://hdl.handle.net/10220/40924
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-81670
record_format dspace
spelling sg-ntu-dr.10356-816702020-03-07T13:56:08Z Joint Feature Learning for Face Recognition Lu, Jiwen Liong, Venice Erin Wang, Gang Moulin, Pierre School of Electrical and Electronic Engineering Face recognition Feature learning This paper presents a new joint feature learning (JFL) approach to automatically learn feature representation from raw pixels for face recognition. Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. Since different face regions have different physical characteristics, we propose to use different feature dictionaries to represent them, and to learn multiple yet related feature projection matrices for these regions simultaneously. Hence position-specific discriminative information can be exploited for face representation. Having learned these feature projections for different face regions, we perform spatial pooling for face patches within each region to enhance the representative power of the learned features. Moreover, we stack our JFL model into a deep architecture to exploit hierarchical information for feature representation and further improve the recognition performance. Experimental results on five widely used face data sets show the effectiveness of our proposed approach. ASTAR (Agency for Sci., Tech. and Research, S’pore) 2016-07-13T02:33:34Z 2019-12-06T14:35:51Z 2016-07-13T02:33:34Z 2019-12-06T14:35:51Z 2015 Journal Article Lu, J., Liong, V. E., Wang, G., & Moulin, P. (2015). Joint Feature Learning for Face Recognition. IEEE Transactions on Information Forensics and Security, 10(7), 1371-1383. 1556-6013 https://hdl.handle.net/10356/81670 http://hdl.handle.net/10220/40924 10.1109/TIFS.2015.2408431 en IEEE Transactions on Information Forensics and Security © 2015 IEEE.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Face recognition
Feature learning
spellingShingle Face recognition
Feature learning
Lu, Jiwen
Liong, Venice Erin
Wang, Gang
Moulin, Pierre
Joint Feature Learning for Face Recognition
description This paper presents a new joint feature learning (JFL) approach to automatically learn feature representation from raw pixels for face recognition. Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. Since different face regions have different physical characteristics, we propose to use different feature dictionaries to represent them, and to learn multiple yet related feature projection matrices for these regions simultaneously. Hence position-specific discriminative information can be exploited for face representation. Having learned these feature projections for different face regions, we perform spatial pooling for face patches within each region to enhance the representative power of the learned features. Moreover, we stack our JFL model into a deep architecture to exploit hierarchical information for feature representation and further improve the recognition performance. Experimental results on five widely used face data sets show the effectiveness of our proposed approach.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Lu, Jiwen
Liong, Venice Erin
Wang, Gang
Moulin, Pierre
format Article
author Lu, Jiwen
Liong, Venice Erin
Wang, Gang
Moulin, Pierre
author_sort Lu, Jiwen
title Joint Feature Learning for Face Recognition
title_short Joint Feature Learning for Face Recognition
title_full Joint Feature Learning for Face Recognition
title_fullStr Joint Feature Learning for Face Recognition
title_full_unstemmed Joint Feature Learning for Face Recognition
title_sort joint feature learning for face recognition
publishDate 2016
url https://hdl.handle.net/10356/81670
http://hdl.handle.net/10220/40924
_version_ 1681048036716838912