Illumination Robust Face Recognition Using Spatial Expansion Local Histogram Equalization and Locally Linear Regression Classification

Pei Chun Chang, Yong-Sheng Chen, Chang Hsing Lee, Cheng Chang Lien, Chin Chuan Han

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

1 Scopus citations

Abstract

Robust face recognition under illumination variations is a critical problem in a face recognition system, particularly for face recognition in the wild. In this paper, a face image preprocessing approach, called spatial expansion local histogram equalization (SELHE), is proposed to enhance face images due to illumination variations. First, a face image is divided into several non-overlapped blocks. Then, local histogram equalization with spatial expansion is proposed to enhance the contrast of each local image block. Local linear regression classification will then be used to recognize the enhanced image blocks. Experiments performed on the Yale B and Yale B extended databases have shown that the proposed approach yields promising recognition accuracy.

Original languageEnglish
Title of host publication2018 3rd International Conference on Computer and Communication Systems, ICCCS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages482-486
Number of pages5
ISBN (Print)9781538663509
DOIs
StatePublished - 11 Sep 2018
Event3rd International Conference on Computer and Communication Systems, ICCCS 2018 - Nagoya, Japan
Duration: 27 Apr 201830 Apr 2018

Publication series

Name2018 3rd International Conference on Computer and Communication Systems, ICCCS 2018

Conference

Conference3rd International Conference on Computer and Communication Systems, ICCCS 2018
Country/TerritoryJapan
CityNagoya
Period27/04/1830/04/18

Keywords

  • face recognition
  • histogram equalization
  • linear regression classification

Fingerprint

Dive into the research topics of 'Illumination Robust Face Recognition Using Spatial Expansion Local Histogram Equalization and Locally Linear Regression Classification'. Together they form a unique fingerprint.

Cite this