An improved method for illumination invariant face recognition based on adaptive rescaling DCT coefficient in logarithm domain

Chao Yu, Xiaoqun Zhao, Sei Ichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents an improved method for robust face recognition using illumination normalization based on Discrete Cosine Transform (DCT) in logarithm domain. Two novel coefficients are designed to identify the lighting condition (LC), based on which the low-frequency DCT coefficients are adaptively rescaled except the first one (DC). As a result variations under different illumination conditions are minimized meanwhile original information contained in low-frequency is comparatively well preserved. Results of experiments on Yale B database and Extended Yale B database show that proposed method has better performance under variational input illumination conditions. The proposed method is fast in computation and could be easily implemented into real time face recognition systems.

Original languageEnglish
Title of host publicationAdvances in Computer, Communication, Control and Automation
Pages297-304
Number of pages8
DOIs
Publication statusPublished - 2011 Dec 1
Event2011 International Conference on Computer, Communication, Control and Automation, 3CA 2011 - Zhuhai, China
Duration: 2011 Nov 192011 Nov 20

Publication series

NameLecture Notes in Electrical Engineering
Volume121 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference2011 International Conference on Computer, Communication, Control and Automation, 3CA 2011
CountryChina
CityZhuhai
Period11/11/1911/11/20

Keywords

  • DCT
  • LC coefficient
  • face recognition
  • illumination invariant

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'An improved method for illumination invariant face recognition based on adaptive rescaling DCT coefficient in logarithm domain'. Together they form a unique fingerprint.

Cite this