Face recognition using VQ histogram in compressed DCT domain

Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


In this paper, we propose a novel algorithm using vector quantization (VQ) histogram for facial image recognition in DCT domain. Firstly, feature vectors of facial image are generated by using DCT (Discrete Cosine transform) coefficients in low frequency domains. Then codevector referred count histogram, which is utilized as a very effective personal feature value, is obtained by Vector Quantization (VQ) processing. Publicly available AT&T database of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions, is used to evaluate the performance of the proposed algorithm. Experimental results show face recognition using proposed feature vector is very efficient. The highest average recognition rate of 94.8% is obtained. Furthermore, combining a region-division (RD) method to add the geometric information of the face, top1 recognition rate of 96.4% is obtained by using FB task (1195 images) in the standard FERET database.

Original languageEnglish
Pages (from-to)395-404
Number of pages10
JournalJournal of Convergence Information Technology
Issue number1
Publication statusPublished - 2012 Jan


  • DCT domain
  • Face recognition
  • Vector quantization (VQ)

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications


Dive into the research topics of 'Face recognition using VQ histogram in compressed DCT domain'. Together they form a unique fingerprint.

Cite this