Image factorization and feature fusion for enhancing robot vision in human face recognition

Hui Yu; Zhaojie Ju; Honghai Liu

doi:10.1109/IJCNN.2014.6889675

Image factorization and feature fusion for enhancing robot vision in human face recognition

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

222 Downloads (Pure)

Abstract

Illumination variation has been a challenging problem for face recognition in robot vision. To reduce the effect caused by illumination variation, a lot of studies have been explored. The Total Variation (TV) method is particular used to
factorize images into a low frequency component and a high frequency one. However, the low frequency component still contains significant intrinsic features resulting in failure in face recognition in some cases. In this paper, we propose to further extract illumination invariant features from face images under
uncontrolled varying lighting conditions. The Nonsampled Contourlet Transform (NSCT) method is employed to enhance the extraction of intrinsic feature. The combined factorization model is very effective in the experiment on the Yale database.

Original language	English
Title of host publication	Proceedings of the 2014 international joint conference on neural networks (IJCNN 2014)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	981-986
ISBN (Electronic)	2161-4393 (ISSN)
ISBN (Print)	978-1-4799-1482-1
DOIs	https://doi.org/10.1109/IJCNN.2014.6889675
Publication status	Published - Nov 2014
Event	IEEE 2014 International Joint Conference on Neural Networks - Beijing, China Duration: 6 Jul 2014 → 11 Jul 2014

Conference

Conference	IEEE 2014 International Joint Conference on Neural Networks
Country/Territory	China
City	Beijing
Period	6/07/14 → 11/07/14

Access to Document

10.1109/IJCNN.2014.6889675

Image_Factorization_for_Enhancing_Robot_Vision_in_Human_Face_Recognition
© © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 3.26 MB

Cite this

@inproceedings{e03a3a0537464322906534af6107594d,

title = "Image factorization and feature fusion for enhancing robot vision in human face recognition",

abstract = "Illumination variation has been a challenging problem for face recognition in robot vision. To reduce the effect caused by illumination variation, a lot of studies have been explored. The Total Variation (TV) method is particular used to factorize images into a low frequency component and a high frequency one. However, the low frequency component still contains significant intrinsic features resulting in failure in face recognition in some cases. In this paper, we propose to further extract illumination invariant features from face images under uncontrolled varying lighting conditions. The Nonsampled Contourlet Transform (NSCT) method is employed to enhance the extraction of intrinsic feature. The combined factorization model is very effective in the experiment on the Yale database. ",

author = "Hui Yu and Zhaojie Ju and Honghai Liu",

year = "2014",

month = nov,

doi = "10.1109/IJCNN.2014.6889675",

language = "English",

isbn = "978-1-4799-1482-1",

pages = "981--986",

booktitle = "Proceedings of the 2014 international joint conference on neural networks (IJCNN 2014)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "IEEE 2014 International Joint Conference on Neural Networks ; Conference date: 06-07-2014 Through 11-07-2014",

}

Yu, H, Ju, Z & Liu, H 2014, Image factorization and feature fusion for enhancing robot vision in human face recognition. in Proceedings of the 2014 international joint conference on neural networks (IJCNN 2014). Institute of Electrical and Electronics Engineers Inc., pp. 981-986, IEEE 2014 International Joint Conference on Neural Networks, Beijing, China, 6/07/14. https://doi.org/10.1109/IJCNN.2014.6889675

Image factorization and feature fusion for enhancing robot vision in human face recognition. / Yu, Hui; Ju, Zhaojie ; Liu, Honghai.
Proceedings of the 2014 international joint conference on neural networks (IJCNN 2014). Institute of Electrical and Electronics Engineers Inc., 2014. p. 981-986.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Image factorization and feature fusion for enhancing robot vision in human face recognition

AU - Yu, Hui

AU - Ju, Zhaojie

AU - Liu, Honghai

PY - 2014/11

Y1 - 2014/11

N2 - Illumination variation has been a challenging problem for face recognition in robot vision. To reduce the effect caused by illumination variation, a lot of studies have been explored. The Total Variation (TV) method is particular used to factorize images into a low frequency component and a high frequency one. However, the low frequency component still contains significant intrinsic features resulting in failure in face recognition in some cases. In this paper, we propose to further extract illumination invariant features from face images under uncontrolled varying lighting conditions. The Nonsampled Contourlet Transform (NSCT) method is employed to enhance the extraction of intrinsic feature. The combined factorization model is very effective in the experiment on the Yale database.

AB - Illumination variation has been a challenging problem for face recognition in robot vision. To reduce the effect caused by illumination variation, a lot of studies have been explored. The Total Variation (TV) method is particular used to factorize images into a low frequency component and a high frequency one. However, the low frequency component still contains significant intrinsic features resulting in failure in face recognition in some cases. In this paper, we propose to further extract illumination invariant features from face images under uncontrolled varying lighting conditions. The Nonsampled Contourlet Transform (NSCT) method is employed to enhance the extraction of intrinsic feature. The combined factorization model is very effective in the experiment on the Yale database.

U2 - 10.1109/IJCNN.2014.6889675

DO - 10.1109/IJCNN.2014.6889675

M3 - Conference contribution

SN - 978-1-4799-1482-1

SP - 981

EP - 986

BT - Proceedings of the 2014 international joint conference on neural networks (IJCNN 2014)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE 2014 International Joint Conference on Neural Networks

Y2 - 6 July 2014 through 11 July 2014

ER -

Image factorization and feature fusion for enhancing robot vision in human face recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this