Abstract: In order to solve the defects of traditional maximum 2-D entropy segmentation algorithm, a large amount of calculation, more time consumption, and so on, a maximum 2-D entropy segmentation method based on the improved genetic algorithm was proposed. By improving the mutation operating mode of the genetic algorithm, the speed of the genetic algorithm to find maximum 2-D entropy segmentation threshold was improved, and then image segmentation by using the segmentation algorithm was accelerated.Through theoretical analysis and simulation experiments, the results show that, the running time of the modified model is compressed to 0.95s, which is far lower than the traditional maximum 2-D entropy segmentation method. The modified segmentation method improves the segmentation efficiency and ensures the accuracy of image segmentation.