应用区域间差异性和距离约束函数的图像分割-计算机工程与应用.PDFVIP

Computer Engineering and Applications 计算机工程与应用 2010 ，46 （32 ） 159 应用区域间差异性和距离约束函数的图像分割 1 1 1 2 周昌雄 ，颜廷秦 ，刘淑芬 ，徐荣青 1 1 1 2 ZHOU Chang-xiong ，YAN Ting-qin ，LIU Shu-fen ，XU Rong-qing 1.苏州市职业大学 电子信息工程系，江苏 苏州 215104 2.南京邮电大学 光电工程学院，南京 210003 1.Department of Electronic and Informational Engineering ，Suzhou Vocational College ，Suzhou ，Jiangsu 215104 ，China 2.College of Optoelectronic Engineering ，Nanjing University of Posts and Telecommunications ，Nanjing 210003 ，China E-mail ：handzhou@ ZHOU Chang-xiong ，YAN Ting-qin ，LIU Shu-fen ，et al.Image segmentation based on inter-region dissimilar properties and distance constraint function.Computer Engineering and Applications ，2010 ，46 （32 ）：159-162. Abstract ：In most existing level set models for image segmentation ，it is necessary to constantly re-initialize the level set function ，or to acquire the gradient flow information of the image to restrict the evolution of the curve.A novel image seg- mentation model of level set based on the maximization of the inter-region dissimilarity and the distance-based constraint function is proposed.In this model ，the distance-based constraint function is introduced as the internal energy to ensure that the level set function is always the Signal Distance Function （SDF），so that the constant re-initialization of the level set func- tion during the evolution process is avoided.Meanwhile ，the external energy function （inter-region dissimilarity function ）is con- structed based on the square of the difference between the average grey levels of the target area and the background.This function is maximized to ensure that the zero level set curve converges to the target boundary stably.Experimental results show that the constant re-initialization in traditional models has been eliminated in