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

Chao Yu*, Xiaoqun Zhao, Sei Ichiro Kamata

*この研究の対応する著者

研究成果

抄録

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.

本文言語English
ホスト出版物のタイトルAdvances in Computer, Communication, Control and Automation
ページ297-304
ページ数8
DOI
出版ステータスPublished - 2011
イベント2011 International Conference on Computer, Communication, Control and Automation, 3CA 2011 - Zhuhai, China
継続期間: 2011 11 192011 11 20

出版物シリーズ

名前Lecture Notes in Electrical Engineering
121 LNEE
ISSN(印刷版)1876-1100
ISSN(電子版)1876-1119

Conference

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

ASJC Scopus subject areas

  • 産業および生産工学

フィンガープリント

「An improved method for illumination invariant face recognition based on adaptive rescaling DCT coefficient in logarithm domain」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル