基于半监督聚类的人脸检测方法  

Face Detection Method Based on Semi-supervised Clustering

作　　者：王燕[1] 蒋正午[1] 

机构地区：[1]兰州理工大学计算机与通信学院,兰州730050

出　　处：《计算机工程》2012年第12期182-184,共3页Computer Engineering

基　　金：甘肃省自然科学基金资助项目(1014RJZA009)

摘　　要：将肤色与连续AdaBoost算法相结合进行人脸检测,并引入半监督策略指导肤色聚类从而建立肤色模型。在肤色聚类过程中,提出一种基于半监督的SKDK算法引导肤色聚类,依据各个像素簇的概率统计分布特性得到肤色模型。在此基础上利用数学形态学等知识对图像进行处理,得到人脸候选区域,将其作为连续AdaBoost分类器的输入进行人脸检测。实验结果表明,在多人脸的场景下,该方法的检测效果优于直接使用连续AdaBoost方法进行人脸检测的检测效果。The paper proposes a method of face detection combined color of skin with continuous AdaBoost algorithm.In order to establish skin color model,this paper takes advantage of semi-supervised strategy to guide skin color clustering,and it also proposes a new algorithm SKDK in the process of clustering.skin color model can be established by the probability statistics distribution characteristics of each pixel cluster.On this basis,mathematical morphology of knowledge is used to handle image and find face candidate,which is the input of continuous AdaBoost classifier for final face detection.Experimental results prove that face detection ability of the method is superior to that directly using continuous AdaBoost method for face detection especially in multi-face situation.

关 键 词：人脸检测 半监督策略 聚类 肤色模型 数学形态学 连续ADABOOST 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]