Face recognition based on combination of human perception and local binary pattern

  • Authors:

  • Zhihua Xie;Guodong Liu;Zhijun Fang

  • Affiliations:

  • Key Lab of Optic-Electronic and Communication, Jiangxi Sciences and Technology Normal University, Nanchang, Jiangxi, China;Key Lab of Optic-Electronic and Communication, Jiangxi Sciences and Technology Normal University, Nanchang, Jiangxi, China;School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China

  • Venue:
  • IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Face recognition has recently become very hot research topic in computer vision and multimedia information processing. To integrate the human perception of local micro-pattern to face recognition, this paper proposes an improve LBP face representation based on Weber's law. First, inspired by psychological Weber's law, the human perception of local micro-pattern is defined by the ratio between two terms: one is relative intensity differences of a central pixel against its neighbors and the other is intensity of local central pixel. Second, regarding the perception of local micro-pattern as its weight, the weighted LBP histogram is constructed with the defined weight. Finally, to make full use of the space location information and lessen the complexity of recognition, the partitioning and uniform patterns are applied to get final features. Three face image databases, namely, ORL, Yale and Extended Yale-B, are used to evaluate performance. Experimental results demonstrate the effectiveness and superiority of our proposed face recognition method.