基于肤色模型和梯度算子的正面人脸轮廓提取  

Front Face Contour Extraction Based on Skin Color Model and Gradient Operator

作　　者：吴绿芳[1] 雷蕴奇[1] 魏昇[1] 吴众山[1] 

机构地区：[1]厦门大学信息科学与技术学院,福建厦门361005

出　　处：《电脑与信息技术》2008年第1期1-4,共4页Computer and Information Technology

基　　金：国家高技术研究发展计划(863计划)资助项目;项目编号:2006AA01Z129

摘　　要：文章提出了一种新的正面人脸封闭轮廓提取方法,首先采用肤色模型对肤色区域进行初定位,然后经过筛选去除非人脸区域,最后提取人脸初步轮廓,并结合梯度算子提取下巴轮廓,进而得到一个连续、封闭的人脸轮廓。该算法基本克服了下巴轮廓难以从颈部提取的问题,满足了人脸轮廓特征提取的要求,同时具有较高的时效性。A new extraction method for front face contour is proposed by this paper. Firstly, we locate the skin color regions by using the skin color model. Then, we filter the false face regions and extract the preliminary face contour. Finally, the whole continuous and close face contour is obtained by extracting upper face contour in the face region and by extracting chin contour through a gradient operator. The proposed algorithm basically overcomes the diffculty of extracting the chin contour from the neck, satisfies the demand of face contour feature extraction, and also it has a high time-effectiveness.

关 键 词：肤色模型 轮廓提取 梯度算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]