Partially occluded face completion and recognition

Yue Deng; Dong Li; Xudong Xie; Kin Man Lam; Qionghai Dai

doi:10.1109/ICIP.2009.5413474

Partially occluded face completion and recognition

Yue Deng, Dong Li, Xudong Xie, Kin Man Lam, Qionghai Dai

The Hong Kong Polytechnic University

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

14 Citations (Scopus)

Abstract

This paper proposes a spectral graph based algorithm for face image repairing, which can improve the recognition performance on occluded faces. Our algorithm is called 'guided label-learning', so named from graphical models, and can achieve a high-quality repairing of damaged or occluded faces. We apply our face repairing algorithm in order to produce completed faces, and then use face recognition to evaluate the performance of our algorithm. Experiment results show that, at most, a nearly 30%-increase in the recognition rate can be achieved for occluded faces with the use of our algorithm.

Original language	English
Title of host publication	2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
Publisher	IEEE Computer Society
Pages	4145-4148
Number of pages	4
ISBN (Print)	9781424456543
DOIs	https://doi.org/10.1109/ICIP.2009.5413474
Publication status	Published - 1 Jan 2009
Event	2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt Duration: 7 Nov 2009 → 10 Nov 2009

Conference

Conference	2009 IEEE International Conference on Image Processing, ICIP 2009
Country/Territory	Egypt
City	Cairo
Period	7/11/09 → 10/11/09

Keywords

Face recognition
Guided label-learning
Occluded face completion

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

More information

10.1109/ICIP.2009.5413474

Cite this

@inproceedings{f2b146ea30064a69a0187876505206c2,

title = "Partially occluded face completion and recognition",

abstract = "This paper proposes a spectral graph based algorithm for face image repairing, which can improve the recognition performance on occluded faces. Our algorithm is called 'guided label-learning', so named from graphical models, and can achieve a high-quality repairing of damaged or occluded faces. We apply our face repairing algorithm in order to produce completed faces, and then use face recognition to evaluate the performance of our algorithm. Experiment results show that, at most, a nearly 30%-increase in the recognition rate can be achieved for occluded faces with the use of our algorithm.",

keywords = "Face recognition, Guided label-learning, Occluded face completion",

author = "Yue Deng and Dong Li and Xudong Xie and Lam, {Kin Man} and Qionghai Dai",

year = "2009",

month = jan,

day = "1",

doi = "10.1109/ICIP.2009.5413474",

language = "English",

isbn = "9781424456543",

pages = "4145--4148",

booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",

publisher = "IEEE Computer Society",

address = "United States",

note = "2009 IEEE International Conference on Image Processing, ICIP 2009 ; Conference date: 07-11-2009 Through 10-11-2009",

}

Partially occluded face completion and recognition. / Deng, Yue; Li, Dong; Xie, Xudong et al.
2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 4145-4148 5413474.

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

TY - GEN

T1 - Partially occluded face completion and recognition

AU - Deng, Yue

AU - Li, Dong

AU - Xie, Xudong

AU - Lam, Kin Man

AU - Dai, Qionghai

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This paper proposes a spectral graph based algorithm for face image repairing, which can improve the recognition performance on occluded faces. Our algorithm is called 'guided label-learning', so named from graphical models, and can achieve a high-quality repairing of damaged or occluded faces. We apply our face repairing algorithm in order to produce completed faces, and then use face recognition to evaluate the performance of our algorithm. Experiment results show that, at most, a nearly 30%-increase in the recognition rate can be achieved for occluded faces with the use of our algorithm.

AB - This paper proposes a spectral graph based algorithm for face image repairing, which can improve the recognition performance on occluded faces. Our algorithm is called 'guided label-learning', so named from graphical models, and can achieve a high-quality repairing of damaged or occluded faces. We apply our face repairing algorithm in order to produce completed faces, and then use face recognition to evaluate the performance of our algorithm. Experiment results show that, at most, a nearly 30%-increase in the recognition rate can be achieved for occluded faces with the use of our algorithm.

KW - Face recognition

KW - Guided label-learning

KW - Occluded face completion

UR - http://www.scopus.com/inward/record.url?scp=77951951526&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5413474

DO - 10.1109/ICIP.2009.5413474

M3 - Conference article published in proceeding or book

SN - 9781424456543

SP - 4145

EP - 4148

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

T2 - 2009 IEEE International Conference on Image Processing, ICIP 2009

Y2 - 7 November 2009 through 10 November 2009

ER -

Partially occluded face completion and recognition

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this