Multi-manifold metric learning for face recognition based on image sets
In this paper, we propose a new multi-manifold metric learning (MMML) method for the task of face recognition based on image sets. Different from most existing metric learning algorithms that learn the distance metric for measuring single images, our method aims to learn distance metrics to measu...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2015
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/103837 http://hdl.handle.net/10220/24578 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-103837 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1038372020-03-07T14:02:45Z Multi-manifold metric learning for face recognition based on image sets Huang, Likun Lu, Jiwen Tan, Yap Peng School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision In this paper, we propose a new multi-manifold metric learning (MMML) method for the task of face recognition based on image sets. Different from most existing metric learning algorithms that learn the distance metric for measuring single images, our method aims to learn distance metrics to measure the similarity between manifold pairs. In our method, each image set is modeled as a manifold and then multiple distance metrics among different manifolds are learned. With these distance metrics, the intra-class manifold variations are minimized and inter-class manifold variations are maximized simultaneously. For each person, we learn a distance metric by using such a criterion that all the learned distance metrics are person-specific and thus more discriminative. Our method is extensively evaluated on three widely studied face databases, i.e., Honda/UCSD database, CMU MoBo database and Youtube Celebrities database, and compared to the state-of-the-arts. Experimental results are presented to show the effectiveness of the proposed method. Accepted version 2015-01-12T03:06:25Z 2019-12-06T21:21:21Z 2015-01-12T03:06:25Z 2019-12-06T21:21:21Z 2014 2014 Journal Article Huang, L., Lu, J., & Tan, Y.-P. (2014). Multi-manifold metric learning for face recognition based on image sets. Journal of visual communication and image representation, 25(7), 1774-1783. 1047-3203 https://hdl.handle.net/10356/103837 http://hdl.handle.net/10220/24578 10.1016/j.jvcir.2014.08.006 en Journal of visual communication and image representation © Elsevier Inc. This is the author created version of a work that has been peer reviewed and accepted for publication by Journal of Visual Communication and Image Representation, Elsevier Inc. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1016/j.jvcir.2014.08.006]. 29 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
spellingShingle |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Huang, Likun Lu, Jiwen Tan, Yap Peng Multi-manifold metric learning for face recognition based on image sets |
description |
In this paper, we propose a new multi-manifold metric learning (MMML)
method for the task of face recognition based on image sets. Different from
most existing metric learning algorithms that learn the distance metric for
measuring single images, our method aims to learn distance metrics to measure
the similarity between manifold pairs. In our method, each image set
is modeled as a manifold and then multiple distance metrics among different
manifolds are learned. With these distance metrics, the intra-class manifold
variations are minimized and inter-class manifold variations are maximized
simultaneously. For each person, we learn a distance metric by using such
a criterion that all the learned distance metrics are person-specific and thus
more discriminative. Our method is extensively evaluated on three widely
studied face databases, i.e., Honda/UCSD database, CMU MoBo database
and Youtube Celebrities database, and compared to the state-of-the-arts.
Experimental results are presented to show the effectiveness of the proposed
method. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Huang, Likun Lu, Jiwen Tan, Yap Peng |
format |
Article |
author |
Huang, Likun Lu, Jiwen Tan, Yap Peng |
author_sort |
Huang, Likun |
title |
Multi-manifold metric learning for face recognition based on image sets |
title_short |
Multi-manifold metric learning for face recognition based on image sets |
title_full |
Multi-manifold metric learning for face recognition based on image sets |
title_fullStr |
Multi-manifold metric learning for face recognition based on image sets |
title_full_unstemmed |
Multi-manifold metric learning for face recognition based on image sets |
title_sort |
multi-manifold metric learning for face recognition based on image sets |
publishDate |
2015 |
url |
https://hdl.handle.net/10356/103837 http://hdl.handle.net/10220/24578 |
_version_ |
1681047897364234240 |