Image segmentation is a technique and process of dividing an image into a number of specific, unique areas and extracting the target of interest. Segmentation results directly affect target feature extraction and description, further target identification, classification and image understanding. Due to the complexity and relevance of image information, there is uncertainty and fuzziness in image segmentation. We use the variable precision rough set to represent the image, combining rough entropy and particle swarm optimization algorithm, propose an image segmentation algorithm based on variable precision rough entropy. We obtain the optimal segmentation threshold corresponding to the maximum rough entropy and then divide the image by the binary segmentation method. Experimental results show that the proposed algorithm is superior to the traditional single threshold segmentation method, and has certain practicability and flexibility.