Home // ICSNC 2012, The Seventh International Conference on Systems and Networks Communications // View article

Combined Histogram-based Features of DCT Coefficients in Low-frequency Domains for Face Recognition

Authors:
Qiu Chen
Koji Kotani
Feifei Lee
Tadahiro Ohmi

Keywords: Face recognition; Vector quantizaiton (VQ); Energy histogram; DCT coefficients

Abstract:
Previously, We proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. It can be considered that this algorithm is essential for utilizing the phase information of DCT coefficients by applying binary quantization on the DCT coefficient blocks. In this paper, we newly utilize energy histogram so as to add magnitude information of DCT coefficients. These two histograms, which contain both phase and magnitude information of a DCT transformed facial image, are utilized as a very effective personal value. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogram-based features of DCT coefficients in low frequency domains can achieve much higher recognition rate.

Pages: 108 to 112

Copyright: Copyright (c) IARIA, 2012

Publication date: November 18, 2012

Published in: conference

ISSN: 2163-9027

ISBN: 978-1-61208-231-8

Location: Lisbon, Portugal

Dates: from November 18, 2012 to November 23, 2012