Performance improvement of face recognition algorithms using occluded-region detection

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Citations (Scopus)

Abstract

Facial occlusions such as eyeglasses, hairs and beards decrease the performance of face recognition algorithms. To improve the performance of face recognition algorithms, this paper proposes a novel framework of face recognition combined with the occluded-region detection method. In this paper, we detect occluded regions using Fast-Weighted Principal Component Analysis (FW-PCA) and use the occluded regions as weights for matching face images. To demonstrate the effectiveness of the proposed framework, we use two face recognition algorithms: Local Binary Patterns (LBP) and Phase-Only Correlation (POC). Experimental evaluation using public face image databases indicates performance improvement of the face recognition algorithms for face images with natural and artificial occlusions.

Original languageEnglish
Title of host publicationProceedings - 2013 International Conference on Biometrics, ICB 2013
PublisherIEEE Computer Society
ISBN (Print)9781479903108
DOIs
Publication statusPublished - 2013
Event6th IAPR International Conference on Biometrics, ICB 2013 - Madrid, Spain
Duration: 2013 Jun 42013 Jun 7

Publication series

NameProceedings - 2013 International Conference on Biometrics, ICB 2013

Conference

Conference6th IAPR International Conference on Biometrics, ICB 2013
Country/TerritorySpain
CityMadrid
Period13/6/413/6/7

Fingerprint

Dive into the research topics of 'Performance improvement of face recognition algorithms using occluded-region detection'. Together they form a unique fingerprint.

Cite this