Title: Face recognition in colour JPEG compressed domain

Authors: Alireza Sepas-Moghaddam; Mohammad-Shahram Moin

Addresses: Young Researchers and Elite Club, Science and Research Branch, Islamic Azad University, Hesarak, Tehran, 1477893855, Iran ' IT Faculty, ICT Research Center (ITRC), North Kargar Street, Tehran, 1439955471, Iran

Abstract: In spite of the positive role of colour features in pixel domain face recognition systems, previous recognition approaches in JPEG compressed domain have been proposed in grey space. In this study, for the first time, we investigated the effects of JPEG compressed colour features on the efficiency of the state-of-the-art approaches in this domain. To achieve this, a comprehensive set of experiments have been conducted on colour FEI facial database. PCA and ICA methods have been used for extracting feature vectors and reducing the dimension of the extracted features. The results in colour space have been compared with those in grey space and showed the benefit of using the colour features in JPEG compressed domain face recognition in terms of recognition performance. It has also been observed an increase in the class separation and discriminatory power using colour compressed domain features over features extracted in grey space.

Keywords: face recognition; JPEG compressed domain; colour features; colour face database; discriminatory power; biometrics; PCA; ICA; principal component analysis; independent component analysis; feature extraction.

DOI: 10.1504/IJBM.2014.064415

International Journal of Biometrics, 2014 Vol.6 No.3, pp.304 - 320

Received: 28 Sep 2013
Accepted: 13 Jun 2014

Published online: 10 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article