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.
出处
《三峡大学学报(自然科学版)》
CAS
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)
关键词
水平集
人脸轮廓提取
边缘指示函数
支持度变换
level set
facial contour extraction
edge indicator function
support value transform