基于特征选择的皮肤检测混合颜色空间的选取

doi:10.13190/j.jbupt.2017-184

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (1): 24-30.doi: 10.13190/j.jbupt.2017-184

基于特征选择的皮肤检测混合颜色空间的选取

刘新华¹, 赵子谦¹, 旷海兰¹, 马小林¹, 李方敏²

1. 武汉理工大学信息工程学院, 武汉 430070;
2. 长沙学院数学与计算机系, 长沙 410022

收稿日期:2017-08-30 出版日期:2018-02-28 发布日期:2018-01-04
作者简介:刘新华(1974-),男,教授,硕士生导师,E-mail:liuxinhua@whut.edu.cn.
基金资助:
国家自然科学基金项目（61373042，61502361）；湖北省自然科学基金项目（2014CFB869）

Selection of Hybrid Color Space for Skin Detection Based on Feature Selection Method

LIU Xin-hua¹, ZHAO Zi-qian¹, KUANG Hai-lan¹, MA Xiao-lin¹, LI Fang-min²

1. School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China;
2. Department of Mathematics and Computer Science, Changsha University, Changsha 410022, China

Received:2017-08-30 Online:2018-02-28 Published:2018-01-04

摘要/Abstract

摘要： 通过特征选择的方法解决皮肤检测过程中颜色空间的选取问题，针对现有基于互信息的特征选择方法的不足，提出了改进方法：1）使用互信息缩小特征选择范围，然后选择使分类效果最佳的特征子集；2）尝试多种可能的特征子集初始化方案，然后选择其中最优的方案.实验结果和对比分析表明，使用改进后的特征选择方法得到的混合颜色空间，其皮肤检测效果优于传统颜色空间和已有混合颜色空间.

关键词: 皮肤检测, 最优特征空间, 混合颜色空间, 互信息, 特征选择

Abstract: To solve the problem of selecting appropriate color space for skin detection, a feature-selection-based method is exploited and two improvements on traditional method are proposed:Firstly, mutual information is used to narrow the feature selection range, then feature subset which produces the best classification accuracy will be selected; Secondly, a variety of possible feature subset initialization schemes are tested, and then choose feature set that reveal the best result. Experimental results and comparative analysis show that the hybrid color spaces obtained by the improved feature selection method have better skin detection performance than traditional color spaces and existing hybrid color spaces.

Key words: skin detection, optimal feature space, hybrid color space, mutual information, feature selection

中图分类号:

TP18

刘新华, 赵子谦, 旷海兰, 马小林, 李方敏. 基于特征选择的皮肤检测混合颜色空间的选取[J]. 北京邮电大学学报, 2018, 41(1): 24-30.

LIU Xin-hua, ZHAO Zi-qian, KUANG Hai-lan, MA Xiao-lin, LI Fang-min. Selection of Hybrid Color Space for Skin Detection Based on Feature Selection Method[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2018, 41(1): 24-30.

参考文献

[1] Albiol A, Torres L, Delp E J, et al. Optimum color spaces for skin detection[C]//IEEE International Conference on Image Processing. NJ:IEEE, 2001:122-124.
[2] Oghaz M M, Maarof M A, Zainal A, et al. A hybrid color space for skin detection using genetic algorithm heuristic search and principal component analysis technique[J]. Plos One, 2015, 10(8):e0134828.
[3] Bergasa L M, Mazo M, Gardel A, et al. Unsupervised and adaptive Gaussian skin-color model[J]. Image & Vision Computing, 2000, 18(12):987-1003.
[4] Chaves-González J M, Vega-Rodríguez M A, Gómez-Pulido J A, et al. Detecting skin in face recognition systems:a color spaces study[J]. Digital Signal Processing, 2010, 20(3):806-823.
[5] Khan R, Hanbury A, Ttinger J, et al. Color based skin classification[J]. Pattern Recognition Letters, 2012, 33(2):157-163.
[6] Subban R, Mishra R. Combining color spaces for human skin detection in color images using skin cluster classifier[C]//International Conference on Advances in Recent Technologies in Electrical and Electronics. Bangalore:[s.n.], 2013:68-73.
[7] De Dios J J, Garcia N. Fast face segmentation in component color space[C]//IEEE International Conference on Image Processing. NJ:IEEE, 2004:191-194.
[8] Terrillon J C, Fukamachi H, Akamatsu S, et al. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images[C]//IEEE International Conference on Automatic Face and Gesture Recognition. NJ:IEEE, 2000:54-63.
[9] Liu Z, Liu C. A hybrid color and frequency features method for face recognition[J]. IEEE Transactions on Image Processing, 2008, 17(10):1975-1980.
[10] Shih P, Liu C, IEEE. Improving the face recognition grand challenge baseline performance using color configurations across color spaces[C]//2006 IEEE International Conference on Image Processing. NJ:IEEE, 2006:1001-1008.
[11] Cover T M, Thomas J A. Elements of information theory[M]. Beijing:Tsinghua University Press, 2005:13-30.
[12] Zheng Y, Kwoh C K. A feature subset selection method based on high-dimensional mutual information[J]. Entropy, 2011, 13(4):860-901.
[13] Kawulok M, Kawulok J, Nalepa J. Spatial-based skin detection using discriminative skin-presence features[J]. Pattern Recognition Letters, 2014, 41:3-13.
[14] Casati Jpb, Moraes Dr, Rodrigues E. SFA:A human skin image database based on FERET and AR facial images[C]//IX workshop de Visao Computational. Rio de Janeiro:[s.n.], 2013.

[1]	霍纬纲, 王星, 梁锐. 融合互信息估计和对抗自编码器的异常检测[J]. 北京邮电大学学报, 2021, 44(5): 28-34.
[2]	刘占峰, 潘甦. 粒子群优化的模糊粗糙集双约简算法[J]. 北京邮电大学学报, 2021, 44(4): 49-55.
[3]	亢伟民, 杨鸿文. 星座成形在超奈奎斯特传输中的应用[J]. 北京邮电大学学报, 2021, 44(1): 32-37.
[4]	彭岩, 赵梓如, 吴婷娴, 王洁. PM_2.5浓度预测与影响因素分析[J]. 北京邮电大学学报, 2019, 42(6): 162-169.
[5]	仇利克, 刘竞, 孙中卫, 赵扬帆. 一种快速的特征选择框架和方法[J]. 北京邮电大学学报, 2019, 42(3): 127-132.
[6]	张俐, 袁玉宇, 王枞. 基于最大相关信息系数的FCBF特征选择算法[J]. 北京邮电大学学报, 2018, 41(4): 86-90.
[7]	蒋成鑫, 吴湛击. 基于低密度叠加编码调制的新型上行非正交多址接入方案[J]. 北京邮电大学学报, 2018, 41(3): 14-19.
[8]	崔鸿雁, 徐帅, 张利锋, Roy E. Welsch, Berthold K. P. Horn. 机器学习中的特征选择方法研究及展望[J]. 北京邮电大学学报, 2018, 41(1): 1-12.
[9]	仇利克, 郭忠文, 刘青, 刘颖健, 仇志金. 基于冗余分析的特征选择算法[J]. 北京邮电大学学报, 2017, 40(1): 36-41.
[10]	张素香. 智能小区的商业智能[J]. 北京邮电大学学报, 2012, 35(5): 94-97.
[11]	张剑，钱宗珏，寿国础，胡怡红. 在线聚类的网络流量识别[J]. 北京邮电大学学报, 2011, 34(1): 103-106.
[12]	牛建伟1 ；沈思思1 ；童超1 ；高小鹏1 ；汪孔桥2. 基于修正交叉视觉皮质模型的图像分割方法[J]. 北京邮电大学学报, 2010, 33(1): 56-60.
[13]	孙跃鹏;刘民;郝井华;吴澄. 基于SVM特征选择的整经轴数预测算法[J]. 北京邮电大学学报, 2009, 32(6): 88-92.
[14]	熊文;王枞. 改进粒子群与支持向量机混合的特征变换[J]. 北京邮电大学学报, 2009, 32(6): 24-27.
[15]	李琳;袁超伟;杨睿哲. 一种新的选择BICM-ID混合调制映射方法[J]. 北京邮电大学学报, 2009, 32(6): 32-36.

基于特征选择的皮肤检测混合颜色空间的选取

Selection of Hybrid Color Space for Skin Detection Based on Feature Selection Method

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价