Optimization of color conversion for face recognition

被引:30
作者
Jones, CF [1 ]
Abbott, AL
机构
[1] Virginia Polytech Inst & State Univ, Bradley Dept Elect & Comp Engn, Blacksburg, VA 24061 USA
[2] Seattle Pacific Univ, Dept Comp Sci, Seattle, WA 98119 USA
关键词
face recognition; color image analysis; color conversion; Karhunen-Loeve analysis;
D O I
10.1155/S1110865704401073
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper concerns the conversion of color images to monochromatic form for the purpose of human face recognition. Many face recognition systems operate using monochromatic information alone even when color images are available. In such cases, simple color transformations are commonly used that are not optimal for the face recognition task. We present a framework for selecting the transformation from face imagery using one of three methods: Karhunen-Loeve analysis, linear regression of color distribution, and a genetic algorithm. Experimental results are presented for both the well-known eigenface method and for extraction of Gabor-based face features to demonstrate the potential for improved overall system performance. Using a database of 280 images, our experiments using these methods resulted in performance improvements of approximately 4% to 14%.
引用
收藏
页码:522 / 529
页数:8
相关论文
empty
未找到相关数据