Color face recognition using adaptive feature fusion based on chroma mahalanobis distance map and gray map

Cui Fayi

The color provides much more information than the gray. Considering that the color facial image contains much more identification information than the gray facial image, the chroma Mahalanobis distance map was introduced into color face recognition. Based on the YCbCr color space, the information of chroma and brightness for one color facial image can be separated. Then Mahalanobis distance maps based on chroma information were constructed, at the same time, gray maps based on brightness information can be extracted by orignal color facial images. An algorithm for color face recognition using adaptive feature fusion based on chroma Mahalanobis distance map and gray map was presented. Based on energy values of wavelet packet sub-nodes, normalized feature vectors of chroma Mahalanobis distance maps and gray maps were constructed, respectively. Then identification feature vectors were constructed using several feature fusion methods, and fusion parameters were selected adaptively according to fusion effects. So feature complementation of chroma and brightness was achieved. Results of face recognition were obtained by the classifier based on the variance similarity degree. Experiments show that the algorithm has the characteristics of high recognition rate and good robustness.

1. Hebei Province Key Laboratory of Measurement Technology and Instrumentation,Yanshan University,Qinhuangdao 066004,China

Received Date: 2014-08-05

Rev Recd Date: 2014-09-15

Publish Date: 2015-04-25

Key words:

Abstract: The color provides much more information than the gray. Considering that the color facial image contains much more identification information than the gray facial image, the chroma Mahalanobis distance map was introduced into color face recognition. Based on the YCbCr color space, the information of chroma and brightness for one color facial image can be separated. Then Mahalanobis distance maps based on chroma information were constructed, at the same time, gray maps based on brightness information can be extracted by orignal color facial images. An algorithm for color face recognition using adaptive feature fusion based on chroma Mahalanobis distance map and gray map was presented. Based on energy values of wavelet packet sub-nodes, normalized feature vectors of chroma Mahalanobis distance maps and gray maps were constructed, respectively. Then identification feature vectors were constructed using several feature fusion methods, and fusion parameters were selected adaptively according to fusion effects. So feature complementation of chroma and brightness was achieved. Results of face recognition were obtained by the classifier based on the variance similarity degree. Experiments show that the algorithm has the characteristics of high recognition rate and good robustness.

HTML

Reference (21)

[1]
[2]	OuShanhu, Wang Qianli, Zhu Zheyu. VisualC++.NET Digital Image Processing Technology and Application [M]. Beijing: Tsinghua University Press, 2004: 25-48. (in Chinese) 欧珊瑚, 王倩丽, 朱哲瑜. VisualC++. NET数字图像处理技术与应用 [M]. 北京: 清华大学出版社, 2004: 25-48.
[3]	Yip A W, Sinha P. Contribution of color to face recognition [J]. Perception, 2002, 31(8)：995-1003.
[4]
[5]
[6]	Angelopoulou E. Understanding the color of human skin[C]//Proceedings of Conference on Human Vision and Electronic Imaging VI, 2001: 243-251.
[7]
[8]	Vezhnevets V, Sazonov V, Andreeva A. A survey on pixel-based skin color detection techniques[C]//Proceedings of GraphiCon'03, 2003: 85 -92.
[9]
[10]	Pei S C, Cheng C M. A novel block truncation coding of color images by using quaternion-moment-preserving principle[C]//Proceedings of IEEE International Symposium on Circuits and Systems, 1996: 684-687.
[11]
[12]	Pei S C, Chang J H, Ding J J. Quaternion matrix singular value decomposition and its applications for color image processing[C]//Proceedings of International Conference on Image Processing, 2003: 14-17.
[13]	Zheng Dezhong, Cui Fayi. Face recogniton using wavelet packet feature extraction and variance similarity[J]. Optical Technique, 2010, 36(2): 217-224. (in Chinese) 郑德忠, 崔法毅. 小波包特征提取及方差相似度的人脸识别[J]. 光学技术, 2010, 36(2): 217-224.
[14]
[15]	Yin Juncheng, Liang Bing. Compressing color images with wavelets in MATLAB[J]. Journal of Shanxi Teacher's University(Natural Science Edition), 2002, 16(1): 9-12. (in Chinese) 银俊成, 梁冰. 在MATLAB中运用二维小波压缩彩色图像 [J]. 山西师范大学学报(自然科学版), 2002, 16(1): 9-12.
[16]
[17]	Xu Congdong, Luo Jiarong, Xiao Bingjia. Face detection based on map of mahalanobis distance to skin in color image [J]. Computer Engineering, 2007, 33(12): 196-198. (in Chinese) 徐从东, 罗家融, 肖炳甲. 基于肤色信息马氏距离图的人脸检测[J]. 计算机工程, 2007, 33(12): 196-198.
[18]
[19]	Xu Congdong, Luo Jiarong, Shu Shuangbao. Face recogniton based on RBPNN of mahalanobis distance map for skin color information[J]. Opto- Electronic Engineering, 2008, 35(3): 131-135. (in Chinese) 徐从东, 罗家融, 舒双宝. 肤色信息马氏图的RBPNN人脸识别 [J]. 光电工程, 2008, 35(3): 131-135.
[20]
[21]	Shu Shuangbao, Luo Jiarong, Xu Congdong, et al. Human face detection based on mahalanobis distance map to skin color[J]. Microcomputer Information, 2008, 24(6-1): 268-269, 306. (in Chinese) 舒双宝, 罗家融, 徐从东, 等. 基于肤色马氏距离图的人脸检测 [J]. 微计算机信息 , 2008, 24(6-1): 268-269, 306.

Color face recognition using adaptive feature fusion based on chroma mahalanobis distance map and gray map

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views