An algorithm for eliminating the isolated regions based on connected area in image classification

It is well known that the results of remote sensing image classification contain many small isolated regions. These isolated regions need to be eliminated and merged into the existing classes in the post-processing. The most critical issue among all is how we could recognize the isolated regions, and what strategy we should adopt in automatic elimination. We present in this paper an algorithm for isolated regions´ recognition based on connected area, in isolated region generation, we adopt an improved area filling algorithm in computer graphics. In automatic elimination, we propose a merge strategy which is based on the number of immediate pixels. Experimental results show that our recognition algorithm and merge strategy can effectively and automatically eliminate the isolated regions in the results of remote sensing image classification