利用曲率信息的图像分割改进模型  

Improved image segmentation model using curvature information

作　　者：张万涛[1] 李维国[1] 

机构地区：[1]中国石油大学(华东)数学与计算科学学院,青岛266555

出　　处：《中国图象图形学报》2011年第8期1385-1392,共8页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60971132);中国石油大学(华东)研究生创新基金项目(S10-27);中央高校基本科研业务费专项资金项目(09CX04004A)

摘　　要：首先从理论上分析无须重新初始化的水平集方法的主动轮廓图像分割模型,该模型对一些具有不光滑尖角的图像进行分割时,捕捉这些尖角往往不精确甚至失败;然后对利用边缘检测函数的曲率信息识别出凸尖角并进行分割的方法进行研究,由于此方法没有考虑凹尖角的情形,故对含凹尖角的图像分割效果不理想。为解决该问题,提出利用图像的曲率信息识别出凹尖角,再将其与利用边缘检测函数曲率信息识别凸尖角的方法相结合,进一步修正边缘检测函数,达到准确捕捉物体的凸尖角和凹尖角的目的,保证了分割的准确性。数值实验表明,该方法的分割效果较好。Firstly, an image segmentation method based on level set evolution without re-initialization is studied. This method depends on edge indicator function. However, the method is inaccurate in capturing the sharp comers of the object during image segmention. Then, we analyze the method for image segmentation by using the edge indicator function＇ s curvature information to identify the sharp convex comers. However, the model can only capture the sharp convex comers of the object. When the object has sharp concave comers, the model fails to capture the ones accurately. To overcome this difficulty, we employ the image＇ s curvature information to identify the sharp concave comers, and then combine it with the method of identifying the sharp convex comers by using the edge indicator function＇ s curvature information. By further modifying the edge indicator function to make the method capture both the sharp convex corners and the sharp concave comers of the object more accurately. The numerical experiments show the advantage of the improved model.

关 键 词：图像分割 水平集方法 边缘检测函数 无须重新初始化 尖角 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]