Image Segmentation Based On Variational Level Set Method

Image segmentation is a widely used image processing technology,can greatly reduce the back of advanced image processing data,and does not affect the structure of relevant information,plays a key role in image processing.The error in image segmentation will affect the effectiveness of subsequent image processing,so nearly half a century,have been proposed to improve the precision and accuracy of the segmentation of the various segmentation methods of scholars,made a lot of work in improving the segmentation method.The variational level set is also widely used in the fields of medicine,transportation,industry,agriculture and so on.Samson and other scholars proposed to combine FCM clustering and variational level set method for image segmentation.However,this model needs to be periodically re-initialized,thus affecting the image segmentation time.In this paper,we introduce the H1 regularization of the internal energy function,so that the level set function can not be re-initialized in the evolution process.The method is compared with the traditional Samson model and FCM algorithm.The results show that the proposed method has a shorter running time and better segmentation performance.Secondly,according to the traditional CV model can not very good image segmentation in uneven gray image segmentation,analysis of Lee-Seo and Li-Kim two kinds of improved model in image segmentation performance,a new energy function is proposed,and presents an improved image segmentation algorithm based on graph energy function.The results of the three groups show that compared with the CV model,Lee-Seo model,Li-Kim model,the improved algorithm has the advantages of short running time,less iteration times and good segmentation effect.Finally,this paper makes a summary,and puts forward the future research direction.