Boundary Information Based C_V Model Method for Medical Image Segmentation
Jun Li Han · Journal of Chinese Computer Systems · 2011
The image segmentation is one of the key problems in medical image processing.An improved C_V(Chan Vese) model for medical image segmentation based on boundary information is proposed.Firstly,a term of boundary information is added into the model,incorporating region and boundary information for segmentation.It solves the problem that the traditional C_V method can not use the gradient information.Secondly,the region information term and the mean value definition of the whole image in the traditional C_V model have been changed.It increases the segmentation ability of rich levels gray image.Finally,to overcome the re-initialization,a penalty term of distance function is added into the model,the progress of re-initialization is combined into the framework model.It can speed up the curve evolution and the segmentation.The experiments show that the model is an effective method for medical image segmentation.