An Active Contour Model Based on Region Saliency for Image Segmentation

Image segmentation refers to the process of partitioning an image into some no-overlapped meaningful regions, and it is vital for the higher-level image processing such as image analysis and understanding. During the past few decades, there has been substantial progress in the field of image segmentation and its application. Recently, segmentation algorithms based on active contours have been given wide attention by many internal and foreign researchers due to their variable forms, flexible structure and excellent performance. However, most available active contour models suffer from lacking adaptive initial contour and priori information of target region. In this paper, an active contour model for image segmentation based on visual saliency detection mechanism is proposed. Firstly, priori shape information of target objects in input images which is used to describe the initial curve adaptively is extracted with the visual saliency detection method in order to reduce the influence of initial contour position. Furthermore, the proposed active model can segment images adaptively and automatically, and the segmented results accord with the property of human visual perception. Experimental results demonstrate that the proposed model can achieve better segmentation results than some traditional active contour models. Meanwhile it requires less iteration and is much more computationally efficient.