Restoring occluded regions using FW-PCA for face recognition

Tomoki Hosoi; Sei Nagashima; Koji Kobayashi; Koichi Ito; Takafumi Aoki

doi:10.1109/CVPRW.2012.6239211

Restoring occluded regions using FW-PCA for face recognition

Tomoki Hosoi, Sei Nagashima, Koji Kobayashi, Koichi Ito, Takafumi Aoki

Azbil Corporation

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

14 Citations (Scopus)

Abstract

Occlusions in face images such as eyeglasses, hairs and whiskers decrease the performance of face recognition algorithms. Addressing this problem, this paper proposes a method for restoring occluded regions in face images. The proposed method employs Fast Weighted Principal Component Analysis (FW-PCA), which computes PCA only with effective pixels. The use of FW-PCA makes it possible to detect and restore occluded regions in face images. Through a set of experiments using public face databases, we demonstrate the effectiveness of the proposed method compared with the conventional methods.

Original language	English
Title of host publication	2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
Pages	23-30
Number of pages	8
DOIs	https://doi.org/10.1109/CVPRW.2012.6239211
Publication status	Published - 2012
Event	2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012 - Providence, RI, United States Duration: 2012 Jun 16 → 2012 Jun 21

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012
Country/Territory	United States
City	Providence, RI
Period	12/6/16 → 12/6/21

Access to Document

10.1109/CVPRW.2012.6239211

Cite this

Hosoi, T., Nagashima, S., Kobayashi, K., Ito, K., & Aoki, T. (2012). Restoring occluded regions using FW-PCA for face recognition. In 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012 (pp. 23-30). Article 6239211 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2012.6239211

@inproceedings{285c0e6b6c634f86ab229b4d004ade9f,

title = "Restoring occluded regions using FW-PCA for face recognition",

abstract = "Occlusions in face images such as eyeglasses, hairs and whiskers decrease the performance of face recognition algorithms. Addressing this problem, this paper proposes a method for restoring occluded regions in face images. The proposed method employs Fast Weighted Principal Component Analysis (FW-PCA), which computes PCA only with effective pixels. The use of FW-PCA makes it possible to detect and restore occluded regions in face images. Through a set of experiments using public face databases, we demonstrate the effectiveness of the proposed method compared with the conventional methods.",

author = "Tomoki Hosoi and Sei Nagashima and Koji Kobayashi and Koichi Ito and Takafumi Aoki",

year = "2012",

doi = "10.1109/CVPRW.2012.6239211",

language = "English",

isbn = "9781467316118",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

pages = "23--30",

booktitle = "2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012",

note = "2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012 ; Conference date: 16-06-2012 Through 21-06-2012",

}

Hosoi, T, Nagashima, S, Kobayashi, K, Ito, K & Aoki, T 2012, Restoring occluded regions using FW-PCA for face recognition. in 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012., 6239211, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 23-30, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012, Providence, RI, United States, 12/6/16. https://doi.org/10.1109/CVPRW.2012.6239211

Restoring occluded regions using FW-PCA for face recognition. / Hosoi, Tomoki; Nagashima, Sei; Kobayashi, Koji et al.
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012. 2012. p. 23-30 6239211 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

TY - GEN

T1 - Restoring occluded regions using FW-PCA for face recognition

AU - Hosoi, Tomoki

AU - Nagashima, Sei

AU - Kobayashi, Koji

AU - Ito, Koichi

AU - Aoki, Takafumi

PY - 2012

Y1 - 2012

N2 - Occlusions in face images such as eyeglasses, hairs and whiskers decrease the performance of face recognition algorithms. Addressing this problem, this paper proposes a method for restoring occluded regions in face images. The proposed method employs Fast Weighted Principal Component Analysis (FW-PCA), which computes PCA only with effective pixels. The use of FW-PCA makes it possible to detect and restore occluded regions in face images. Through a set of experiments using public face databases, we demonstrate the effectiveness of the proposed method compared with the conventional methods.

AB - Occlusions in face images such as eyeglasses, hairs and whiskers decrease the performance of face recognition algorithms. Addressing this problem, this paper proposes a method for restoring occluded regions in face images. The proposed method employs Fast Weighted Principal Component Analysis (FW-PCA), which computes PCA only with effective pixels. The use of FW-PCA makes it possible to detect and restore occluded regions in face images. Through a set of experiments using public face databases, we demonstrate the effectiveness of the proposed method compared with the conventional methods.

UR - http://www.scopus.com/inward/record.url?scp=84864985656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864985656&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2012.6239211

DO - 10.1109/CVPRW.2012.6239211

M3 - Conference contribution

AN - SCOPUS:84864985656

SN - 9781467316118

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 23

EP - 30

BT - 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012

T2 - 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2012

Y2 - 16 June 2012 through 21 June 2012

ER -

Restoring occluded regions using FW-PCA for face recognition

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this