Kapur’s entropy underwater image segmentation based on multi-strategy Manta ray foraging optimization

Image segmentation is an important part of image processing, which directly affects the quality of image processing results. Threshold segmentation is the simplest and most widely used segmentation method. However, the best method to determine the threshold has always been a NP-hard problem. Therefore, this paper proposes Kapur’s entropy image segmentation based on multi-strategy manta ray foraging optimization, which has a good effect in CEC 2017 test function and image segmentation. Manta ray foraging optimization (MRFO) is a new intelligent optimization algorithm, which has good searchability, but the local development ability is insufficient, so it can not effectively find a reliable point. To solve this defect, this paper proposes a multi-strategy learning manta ray foraging optimization algorithm, referred to as MSMRFO, which uses saltation learning to speed up the communication within the population and improve the convergence speed, and then puts forward a behavior selection strategy to judge the current situation of the population, Tent disturbance and Gaussian mutation are used to avoid the algorithm falling into local optimization and improve the convergence speed of the algorithm. In the complete CEC 2017 test set, MSMRFO is compared with 8 algorithms, including FA_CL and ASBSO are variants of new algorithms proposed in recent years. The results show that MSMRFO has good optimization ability and universality. In nine underwater image data sets, MSMRFO has better segmentation quality than the other eight algorithms, and the segmentation indicators under high threshold processing has better advantages.