Two parallel strategies of split-merge algorithm for image segmentation

Split-merge algorithm is a general approach for image segmentation based on region growing. Firstly a new merge criterion is proposed to reduce the execution time of the algorithm by decreasing the number of iterations at the merge stage. Then, two strategies for its parallel implementation are discussed by analyzing their difference in load balance, communication complexity and scalability. In the end, the experimental data indicate the efficiency of the algorithm and the parallel strategies.