A split and merge algorithm based on grey theory

In order to split the image region which is interested in, a new split and merge algorithm is presented based on grey theory. This method uses grey correlation theory to make grey relational analysis for the split image. According to the inter-regional comprehensive correlation degree, it can guide whether the region should be merged. Just to analyze data of the borderline of the combined region. Compared to other methods, it is based on grey relational analysis of grey system, and does not require large amounts of data statistics, which is more simple and efficient. The experimental results prove that the algorithm can effectively extract the target area, and has a strong anti-noise capability. It is an effective new method for image segmentation.