Face recognition based on regularized nearest points between image sets

Meng Yang; Pengfei Zhu; Luc Van Gool; Lei Zhang

doi:10.1109/FG.2013.6553727

Face recognition based on regularized nearest points between image sets

Meng Yang, Pengfei Zhu, Luc Van Gool, Lei Zhang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

139 Citations (Scopus)

Abstract

In this paper, a novel regularized nearest points (RNP) method is proposed for image sets based face recognition. By modeling an image set as a regularized affine hull (RAH), two regularized nearest points (RNP), one on each image set's RAH, are automatically determined by an efficient iterative solver. The between-set distance of RNP is then defined by considering both the distance between the RNPs and the structure of image sets. Compared with the recently developed sparse approximated nearest points (SANP) method, RNP has a more concise formulation, less variables and lower time complexity. Extensive experiments on benchmark databases (e.g., Honda/UCSD, CMU Mobo and YouTube databases) clearly show that our proposed RNP consistently outperforms state-of-the-art methods in both accuracy and efficiency.

Original language	English
Title of host publication	2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013
DOIs	https://doi.org/10.1109/FG.2013.6553727
Publication status	Published - 20 Aug 2013
Event	2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013 - Shanghai, China Duration: 22 Apr 2013 → 26 Apr 2013

Conference

Conference	2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013
Country/Territory	China
City	Shanghai
Period	22/04/13 → 26/04/13

Keywords

face recognition
image set
regularized affine hull
regularized nearest points

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

More information

10.1109/FG.2013.6553727

Cite this

@inproceedings{121399fa6e46426da02c173bcaa72a06,

title = "Face recognition based on regularized nearest points between image sets",

abstract = "In this paper, a novel regularized nearest points (RNP) method is proposed for image sets based face recognition. By modeling an image set as a regularized affine hull (RAH), two regularized nearest points (RNP), one on each image set's RAH, are automatically determined by an efficient iterative solver. The between-set distance of RNP is then defined by considering both the distance between the RNPs and the structure of image sets. Compared with the recently developed sparse approximated nearest points (SANP) method, RNP has a more concise formulation, less variables and lower time complexity. Extensive experiments on benchmark databases (e.g., Honda/UCSD, CMU Mobo and YouTube databases) clearly show that our proposed RNP consistently outperforms state-of-the-art methods in both accuracy and efficiency.",

keywords = "face recognition, image set, regularized affine hull, regularized nearest points",

author = "Meng Yang and Pengfei Zhu and {Van Gool}, Luc and Lei Zhang",

year = "2013",

month = aug,

day = "20",

doi = "10.1109/FG.2013.6553727",

language = "English",

isbn = "9781467355452",

booktitle = "2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013",

note = "2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013 ; Conference date: 22-04-2013 Through 26-04-2013",

}

Yang, M, Zhu, P, Van Gool, L & Zhang, L 2013, Face recognition based on regularized nearest points between image sets. in 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013., 6553727, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013, Shanghai, China, 22/04/13. https://doi.org/10.1109/FG.2013.6553727

Face recognition based on regularized nearest points between image sets. / Yang, Meng; Zhu, Pengfei; Van Gool, Luc et al.
2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013. 2013. 6553727.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Face recognition based on regularized nearest points between image sets

AU - Yang, Meng

AU - Zhu, Pengfei

AU - Van Gool, Luc

AU - Zhang, Lei

PY - 2013/8/20

Y1 - 2013/8/20

N2 - In this paper, a novel regularized nearest points (RNP) method is proposed for image sets based face recognition. By modeling an image set as a regularized affine hull (RAH), two regularized nearest points (RNP), one on each image set's RAH, are automatically determined by an efficient iterative solver. The between-set distance of RNP is then defined by considering both the distance between the RNPs and the structure of image sets. Compared with the recently developed sparse approximated nearest points (SANP) method, RNP has a more concise formulation, less variables and lower time complexity. Extensive experiments on benchmark databases (e.g., Honda/UCSD, CMU Mobo and YouTube databases) clearly show that our proposed RNP consistently outperforms state-of-the-art methods in both accuracy and efficiency.

AB - In this paper, a novel regularized nearest points (RNP) method is proposed for image sets based face recognition. By modeling an image set as a regularized affine hull (RAH), two regularized nearest points (RNP), one on each image set's RAH, are automatically determined by an efficient iterative solver. The between-set distance of RNP is then defined by considering both the distance between the RNPs and the structure of image sets. Compared with the recently developed sparse approximated nearest points (SANP) method, RNP has a more concise formulation, less variables and lower time complexity. Extensive experiments on benchmark databases (e.g., Honda/UCSD, CMU Mobo and YouTube databases) clearly show that our proposed RNP consistently outperforms state-of-the-art methods in both accuracy and efficiency.

KW - face recognition

KW - image set

KW - regularized affine hull

KW - regularized nearest points

UR - http://www.scopus.com/inward/record.url?scp=84881540684&partnerID=8YFLogxK

U2 - 10.1109/FG.2013.6553727

DO - 10.1109/FG.2013.6553727

M3 - Conference article published in proceeding or book

SN - 9781467355452

BT - 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013

T2 - 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2013

Y2 - 22 April 2013 through 26 April 2013

ER -

Face recognition based on regularized nearest points between image sets

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this