结合数学形态学和无边界主动轮廓模型的图像分割方法  

Image segmentation algorithm based on mathematical morphology and active edgeless contour model without edges

作　　者：叶昆权[1] 战荫伟[1] 

机构地区：[1]广东工业大学计算机学院,广州510006

出　　处：《计算机应用》2009年第9期2398-2401,2405,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60572078)

摘　　要：为了改善主动轮廓模型的效率,并扩大其适用范围,提出了一种将数学形态学和无边界主动轮廓模型相结合的图像分割方法,先利用数学形态学的平滑算子ASF进行预处理,再利用无边界主动轮廓模型分割平滑图像。试验分析表明,该方法不仅能够提高分割的精确度,还可以减少迭代次数,从而使得主动轮廓模型可以应用到一些背景比较复杂的图像分割中。In order to improve the efficiency of active contour model and expand its application, the authors proposed a new method of image segmentation based on mathematical morphology and active edgeless contour. An image was preprocessed by the smoothing operator, Alternating Sequence Filter （ASF） operator in mathematical morphology before being fed into the segmentation operator of active edgeless contour. Experimental results show that this strategy not only improves the segmentation precision, but also reduces the times of iteration. It also exploits the potential that active edgeless contour can be used in images with complex backgrounds.

关 键 词：数学形态学 无边界主动轮廓模型 水平集方法 图像分割 ASF算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]