Normalized cut as basic tool for remote sensing image

摘要

Some remote sensing image segmentation algorithm can not make full use of local and global information and Normalized has NP-hard problem. In order to solve the problems, image can be described through the graph model and the Normalized cut can be used to cut graph for image segmentation. Watershed algorithm is applied to create the initial segments, and then Normalized cut is used to segment among regions. Experimental result shows that the method is effective.