一种改进的snake算法在人脸检测定位中的应用

Application of An Improved Snake Model in Face Location Based on Skin-Color

在基于彩色图像中的人脸检测的人脸定位问题上,针对snake算法受能量函数的初始状态影响大等缺点,提出了一种改进的snake算法。引入目标图像的质心和目标的最大拉长度作为优先信息确定snake的初始状态,很好地弥补了snake算法的不足。同时减小了搜索的范围,降低了复杂程度,增加了实时性,定位效果也得到大大的提高。

In image processing and computer vision, snake （active contour model） is an effective tool in implementing edge detection or contour extraction of object, But the snake algorithm has the deadly shortcoming - the result is affected by the origin position. In this paper,we propose a new modified algorithm combining centric algorithm into the snake algorithm,so to get the priority information of the origin position. The algorithm reduces sensitivity to initialization while providing superior performance. Finally the results of the computer simulation show the advantage of the new algorithm.