基于支持度变换的水平集人脸轮廓提取方法  

A Level Set Method for Facial Contour Extraction Based on Support Value Transform

作　　者：杨长才[1] 郑胜[1,2] 叶瑾[1] 

机构地区：[1]三峡大学电气信息学院智能视觉与图像信息研究所,湖北宜昌443002 [2]华中科技大学电子与信息工程系,武汉430074

出　　处：《三峡大学学报（自然科学版）》2008年第5期64-67,共4页Journal of China Three Gorges University：Natural Sciences

基　　金：国家自然科学基金(60572048);湖北省教育厅自然科学基金(D200613003)

摘　　要：提出了一种新的人脸轮廓提取方法,该方法将水平集与支持度相结合.首先将人脸图像进行支持度变换得到支持度图像,在此基础上,用支持度图像计算几何活动轮廓模型的边缘指示函数,在演化过程中先选取参数较小的边缘指示函数,使得边缘指示函数对眉毛不敏感,演化曲线过眉毛后选取参数较大的边缘指示函数,使得演化正确收敛于人脸轮廓.实验结果表明该方法的人脸轮廓提取效果较好,收敛速度快.A novel facial contour extraction method is proposed, which combines the level set method and the support vector transform. The support value image is obtained by using support value transform. Then the level set method uses the support value image to compute the edge indicator. In order to avoid the effect of the eyebrow, the small parameter of edge indicator function first is used. After the evolving curve evolved across the eyebrow, the large parameter of edge indicator function is chosen. Then the evolving curve stops when it arrives to the facial contour. The experimental results show that the proposed method has advantages over the direct geometric active contours in converging speed and facial contour extraction accuracy.

关 键 词：水平集 人脸轮廓提取 边缘指示函数 支持度变换 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]