A novel texture image segmentation model based on multi-scale structure

Using neighborhood information from different scales in an effective way for object segmentation, however, remains a difficult problem. In this paper, we propose a novel method which incorporates the multi-scale structure into intensity information. The multi-scale structure is proposed as structure information to describe the texture feature of image. We select eight points as the sample components of each layer and further solve the maximum variance between eight components and center pixel. In addition, the multi-scale structure can be suitably used to extract the texture information of image. Then, by combining texture information with intensity information, we use level set method to obtain the segmentation results. Experiments using synthetic and real natural scene images demonstrate the superior performance of the proposed method.