Title: Spectral Regression dimension reduction for multiple features facial image retrieval

Authors: Bailing Zhang; Yongsheng Gao

Addresses: Department of Computer Science and Software Engineering, Xi'an Jiaotong-Liverpool University, Suzhou 215123, China. ' School of Engineering, Griffith University, QLD 4111, Australia

Abstract: Face retrieval has received much attention in recent years. This paper comparatively studied five feature description methods for face representation, including Local Binary Pattern (LBP), Gabor feature, Gray Level Co-occurrence Matrices (GLCM), Pyramid Histogram of Oriented Gradient (PHOG) and Curvelet Transform (CT). The problem of large dimensionalities of the extracted features was addressed by employing a manifold learning method called Spectral Regression (SR). A fusion scheme was proposed by aggregating the distance metrics. Experiments illustrated that dimension reduced features are more efficient and the fusion scheme can offer much enhanced performance. A 98% rank 1 accuracy was obtained for the AR faces and 92% for the FERET faces.

Keywords: face images; face retrieval; image retrieval; dimension reduction; multiple feature fusion; LBP; local binary pattern; Gabor feature; curvelet transform; PHOG; pyramid histogram of oriented gradient; feature extraction; biometrics.

DOI: 10.1504/IJBM.2012.044296

International Journal of Biometrics, 2012 Vol.4 No.1, pp.77 - 101

Received: 04 Jan 2011
Accepted: 21 Apr 2011

Published online: 17 Dec 2011 *

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