Novel Image Segmentation Methods Based on Improved Ncut Algorithm

Image segmentation is an important process from image processing to image analysis and scene understanding. Targets of different scales in an image may belong to different classes. Single scale image segmentation methods are prone to over-segmentation or under-segmentation. Combining MeanShfit and Ncut multiscale sampling image segmentation methods, the image is smoothed by MeanShift algorithm and the edges are preserved. Clustering using weights (similarities) between two pixels by Ncut method, this method can be applied to remote sensing image segmentation. In order to solve the problems of high time complexity and long calculation time of Ncut algorithm, firstly, the entropy rate superpixel segmentation algorithm is used to over-segment the image. The algorithm divides the image into a series of compact regions with good regional consistency, Combining Ncut method to solve the weights of similarity between two superpixels to determine the attribution of the region can reduce the segmentation time. Experiments show that this method can use multiscale information for image segmentation effectively. The first method can be applied to remote sensing image segmentation, and the second method can improve the efficiency of Ncut which is suitable for natural scene image segmentation.