针对具有严重遮挡的密集人群检测，提出一种结合肤色检测和头发检测的人头区域检测方法. 首先采用多色彩空间肤色检测方法提取图像中的肤色区域；然后根据头发的发色和纹理边缘两个特征建立混合高斯模型，对发色区域进行分割和提取；最后融合以上两检测区域实现人头区域的检测. 实验结果表明，该方法可以得到比较准确而完整的目标区域，具有较高的实用性.
As occlusion occurs frequently in detecting dense crowd of persons, head detection based on Adaboost performs poorly. This paper presents an approach combining skin and hair detection to achieve more reliable head detection. Skin regions in an image are extracted using several color spaces including HSV,
RGB and XYZ. Hair is extracted with a MOG model of the hair color and hair edge texture. The skin and hair regions are fused to give a head region. Experimental results show that the method has a high accuracy and can provide satisfactory results.
[1] GHOMSHEH A N, TALEBPOUR A, BASSERI M. Regional skin detection based on eliminating skin-like Lambertian surfaces [C]//2011 IEEE Symposium on Computers & Informatics, 2011: 307-312.
[2] VIOLA Paul, JONES Michael J. Robust real-time face detection [J]. International Journal of Computer Vision, 2004, 57(2): 137-154.
[3] YANG Der Wei, CHEN Chun Wei, CHANG Che Hao. Face detection architecture design using hybrid skin color detection and cascade of classifiers [C]//2012 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), 2012: 543-546.
[4] LIU Le Yuan, SANG Nong, YANG Sai Yong, HUANG Rui. Real-time skin color detection under rapidly changing illumination conditions [J]. IEEE Transactions on Consumer Electronics, August, 2011, 57(3): 1295-1302.
[5] GHOMSHEH A. Nadian, TALEBPOUR A, BASSERI M. Skin detection based on eliminating skin-like Lambertian surfaces [C]//2011 IEEE Symposium on Computers & Informatics (ISCI), 2011: 307-312.
[6] VEZHNEVETS V, SAZONOV V, ANDREEVA A. A survey on pixel-based skin color detection techniques [C]//International Conference GraphiCon, 2003(3): 85-92.
[7] 傅文林，胡福乔. 基于mean shift的头发自动检测 [J]. 微型电脑应用，2010, 26(9): 62-64.
FU Wenlin, HU Fuqiao. Hair detection with mean shift [J]. Microcomputer Applications, 2010, 26(9): 62-64. (in Chinese)
[8] YACOOB Yaser, DAVIS Larry S. Detection and analysis of hair [J]. IEEE Transactions on Pattern analysis and machine intelligence, 2006, 28(7): 1164-1169. (in Chinese)
[9] 徐涛，冯志全，吴鹏. 与颜色空间选择无关的肤色检测方法[J]. 计算机复辅助设计与图形学学报，2013, 25(1): 49-54
XU Tao, FENG Zhiquan, WU Peng. Skin Color detection without considering the choice of color space [J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(1): 49-54. (in Chinese)
[10] 曾飞，蔡灿辉. 自适应肤色检测算法的研究[J]. 微型机与应用，2011(4): 37-40.
ZENG Fei, CAI Canhui. Study on adaptive skin color detection algorithm [J]. Image Processing and Multimedia Technology, 2011(4): 37-40. (in Chinese)
[11] 李明瑞，傅明，曹敦. 基于肤色检测的AdaBoost人脸检测算法改进[J]. 计算机工程，38(19): 147-150.
LI Ming Rui, FU Ming, CAO Dun. Improvement of AdaBoost face detection algorithm based on skin color detection [J]. Computer Engineering, 38(19): 147-150. (in Chinese)
