Extracting discriminative color features for face recognition

Document Type

Article

Publication Date

10-15-2011

Abstract

This paper presents a discriminative color features (DCF) method, which applies a simple yet effective color model, a novel similarity measure, and effective color feature extraction methods, for improving face recognition performance. First, the new color model is constructed according to the principle of Ockham's razor from a number of available models that take advantage of the subtraction of the primary colors for boosting pattern recognition performance. Second, the novel similarity measure integrates both the angular and the distance information for improving upon the broadly applied similarity measures. Finally, the discriminative color features are extracted from a compact color image representation by means of discriminant analysis with enhanced generalization capabilities. Experiments on the Face Recognition Grand Challenge (FRGC) version 2 Experiment 4, which contains 12,776 training images, 16,028 controlled target images, and 8,014 uncontrolled query images, show the feasibility of the proposed method. © 2011 Elsevier B.V. All rights reserved.

Identifier

80052533440 (Scopus)

Publication Title

Pattern Recognition Letters

External Full Text Location

https://doi.org/10.1016/j.patrec.2011.07.024

ISSN

01678655

First Page

1796

Last Page

1804

Issue

14

Volume

32

This document is currently not available here.

Share

COinS