Localized multifeature metric learning for image-set-based face recognition

This paper presents a new approach to image-set-based face recognition, where each training and testing example is a set of face images captured from varying poses, illuminations, expressions, and resolutions. While a number of image set based face recognition methods have been proposed in recent ye...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu, Jiwen, Wang, Gang, Moulin, Pierre
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/89373
http://hdl.handle.net/10220/44902
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-89373
record_format dspace
spelling sg-ntu-dr.10356-893732020-03-07T14:02:37Z Localized multifeature metric learning for image-set-based face recognition Lu, Jiwen Wang, Gang Moulin, Pierre School of Electrical and Electronic Engineering Face Recognition Image Set Classification This paper presents a new approach to image-set-based face recognition, where each training and testing example is a set of face images captured from varying poses, illuminations, expressions, and resolutions. While a number of image set based face recognition methods have been proposed in recent years, most of them model each face image set as a single linear subspace or as the union of linear subspaces, which may lose some discriminative information for face image set representation. To address this shortcoming, we propose exploiting statistics information as feature representations for face image sets and develop a localized multikernel metric learning algorithm to effectively combine different statistics for recognition. Moreover, we propose a localized multikernel multimetric learning method to jointly learn multiple feature-specific distance metrics in the kernel spaces, one for each statistic feature, to better exploit complementary information for recognition. Our methods achieve state-of-the-art performance on four widely used video face datasets including the Honda, MoBo, YouTube Celebrities, and YouTube Face datasets. MOE (Min. of Education, S’pore) 2018-05-30T03:04:41Z 2019-12-06T17:24:03Z 2018-05-30T03:04:41Z 2019-12-06T17:24:03Z 2015 Journal Article Lu, J., Wang, G., & Moulin, P. (2016). Localized multifeature metric learning for image-set-based face recognition. IEEE Transactions on Circuits and Systems for Video Technology, 26(3), 529-540. 1051-8215 https://hdl.handle.net/10356/89373 http://hdl.handle.net/10220/44902 10.1109/TCSVT.2015.2412831 en IEEE Transactions on Circuits and Systems for Video Technology © 2015 IEEE.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Face Recognition
Image Set Classification
spellingShingle Face Recognition
Image Set Classification
Lu, Jiwen
Wang, Gang
Moulin, Pierre
Localized multifeature metric learning for image-set-based face recognition
description This paper presents a new approach to image-set-based face recognition, where each training and testing example is a set of face images captured from varying poses, illuminations, expressions, and resolutions. While a number of image set based face recognition methods have been proposed in recent years, most of them model each face image set as a single linear subspace or as the union of linear subspaces, which may lose some discriminative information for face image set representation. To address this shortcoming, we propose exploiting statistics information as feature representations for face image sets and develop a localized multikernel metric learning algorithm to effectively combine different statistics for recognition. Moreover, we propose a localized multikernel multimetric learning method to jointly learn multiple feature-specific distance metrics in the kernel spaces, one for each statistic feature, to better exploit complementary information for recognition. Our methods achieve state-of-the-art performance on four widely used video face datasets including the Honda, MoBo, YouTube Celebrities, and YouTube Face datasets.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Lu, Jiwen
Wang, Gang
Moulin, Pierre
format Article
author Lu, Jiwen
Wang, Gang
Moulin, Pierre
author_sort Lu, Jiwen
title Localized multifeature metric learning for image-set-based face recognition
title_short Localized multifeature metric learning for image-set-based face recognition
title_full Localized multifeature metric learning for image-set-based face recognition
title_fullStr Localized multifeature metric learning for image-set-based face recognition
title_full_unstemmed Localized multifeature metric learning for image-set-based face recognition
title_sort localized multifeature metric learning for image-set-based face recognition
publishDate 2018
url https://hdl.handle.net/10356/89373
http://hdl.handle.net/10220/44902
_version_ 1681034345818619904