基于支持向量机的肤色滤波器  

A method of Complexion Detection based on SVM

作　　者：李素梅[1] 张延炘[1] 董磊[2] 常胜江[1] 申金媛[1] 

机构地区：[1]南开大学信息技术科学学院,教育部光电信息技术重点实验室,天津300071 [2]河北农业大学理学院,保定071001

出　　处：《光子学报》2006年第2期304-307,共4页Acta Photonica Sinica

基　　金：天津市自然科学基金重点项目(023800811);国家自然科学基金(60277022;60477009);博士点基金(20030055022)资助

摘　　要：为了探测图像中的肤色像素,提出了一种新的方法—支持向量机(SVMSupport VectorMachine)方法.它是一种基于肤色的非特定人的面部定位方法,是非接触人机交互技术和机器视觉中的一个重要内容.实验结果表明,采用支持向量机方法较传统人工神经网络方法不仅有更高的探测准确性,而且具有更好的推广性能.由于SVM采用结构风险最小化(SRMStructural RiskMini mization)准则,在最小化训练误差(经验风险)的同时,尽量缩小模型预测误差的上界,从而使模型有更好的泛化能力.A detection method of complexion based on SVM is proposed in this paper. The technique is an approach for locating faces in a scene image based on the detection of skin color of an unspecific human which is essentially important in development of contact free human-machine-interaction （HMI） as well as in machine visions. The simulation results show that it may not only get better rate of correct recognition of complexion than that by using traditional artificial neural network but also is better in generalization. This is because that according the criteria of structural risk minimization of support vector machine （SVM）, the errors between sample-data and model-data are minimized and the upper bound of predicting error of the model is also decreased simultaneously.

关 键 词：人工神经网络 支持向量机 肤色滤波 机器视觉 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP18[自动化与计算机技术—控制科学与工程]