Image segmentation technology has become a key technology from image processing to image analysis. As the current image segmentation algorithms still have many defects, it is becoming more and more important to develop a suitable image segmentation algorithm. Although there are many achievements in this area, they all have shortcomings. In order to solve the shortcomings of traditional image segmentation algorithms, this article combines the neutrosophy image segmentation algorithm of LPG&PCA and improves the original FCM algorithm through in-depth research on the neutrosophy image segmentation method. After the experiment, it is found that when the improved algorithm is the lowest index function, the value of the original FCM algorithm is 0.8531, the value of the improved algorithm is 0.4751, and the categories of the original FCM algorithm and the improved algorithm are both 7, indicating the improved algorithm At the lowest exponential function, the correct clustering category can be obtained like the original FCM algorithm.