What Kind of Color Spaces is Suitable for Color Face Recognition?

• NCJ Number: 305990
• Journal: Neurocomputing Volume: 73 Issue: 10-12 Dated: JUN 2010 Pages: 2140-2146
• Author(s): Jian Yang; Chengjun Liu; Jing-yu Yang
• Date Published: June 2010
• Length: 7 pages
• Grant Number(s): 2006-IJ-CX-K033
• Sponsoring Agency: National Institute of Justice (NIJ)
• Publication Format: Article
• Language: English
• Country: United States of America

Annotation

Human faces display different color and recent research efforts show that color is useful for face recognition, so this paper presents a discriminant color space method and demonstrates its effectiveness using the FRGC Experiment 4 database and the AR database.

Abstract

The authors found that the discriminant color space is an approximate double-zero-sum (DZS) color space, and further determined that a color space with DZS characteristic is more powerful than other color spaces without this characteristic. In addition, they provide the justification for why the DZS color spaces are more effective than non-DZS color spaces for face verification and recognition from the mutual correlation perspective. (Published abstract provided)