Fusion of color, local spatial and global frequency information for face recognition

Zhiming Liu, Chengjun Liu

Research output: Contribution to journalArticlepeer-review

108 Scopus citations

Abstract

This paper presents a novel face recognition method by means of fusing color, local spatial and global frequency information. Specifically, the proposed method fuses the multiple features derived from a hybrid color space, the Gabor image representation, the local binary patterns (LBP), and the discrete cosine transform (DCT) of the input image. The novelty of this paper is threefold. First, a hybrid color space, the RCrQ color space, is constructed by combining the R component image of the RGB color space and the chromatic component images, Cr and Q, of the YCbCr and YIQ color spaces, respectively. The RCrQ hybrid color space, whose component images possess complementary characteristics, enhances the discriminating power for face recognition. Second, three effective image encoding methods are proposed for the component images in the RCrQ hybrid color space to extract features: (i) a patch-based Gabor image representation for the R component image, (ii) a multi-resolution LBP feature fusion scheme for the Cr component image, and (iii) a component-based DCT multiple face encoding for the Q component image. Finally, at the decision level, the similarity matrices generated using the three component images in the RCrQ hybrid color space are fused using a weighted sum rule. Experiments on the Face Recognition Grand Challenge (FRGC) version 2 Experiment 4 show that the proposed method improves face recognition performance significantly. In particular, the proposed method achieves the face verification rate (ROC III curve) of 92.43%, at the false accept rate of 0.1%, compared to the FRGC baseline performance of 11.86% face verification rate at the same false accept rate.

Original languageEnglish (US)
Pages (from-to)2882-2890
Number of pages9
JournalPattern Recognition
Volume43
Issue number8
DOIs
StatePublished - Aug 1 2010

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Keywords

  • Face Recognition Grand Challenge (FRGC)
  • Gabor image representation
  • Local binary patterns (LBP)
  • The RCQ hybrid color space
  • The RGB color space
  • The YCC color space
  • The YIQ color space

Fingerprint

Dive into the research topics of 'Fusion of color, local spatial and global frequency information for face recognition'. Together they form a unique fingerprint.

Cite this