A Superpixel Segmentation Method Based on Fuzzy Theory

Abstract

The invention relates to a superpixel segmentation method based on the fuzzy theory. The superpixel segmentation method improves fitness of superpixel edges and original image edges, and segmented superpixels have an undiversified internal structure and uniform gray scale. The superpixel segmentation method comprises steps of 1) processing images and initializing cluster centers; 2) adding coordinate distances of pixel points into the fuzzy C-means clustering algorithm and establishing an objective function; 3) updating a membership matrix; 4) updating cluster centers with gray scale values and coordinates included; 5) repeating steps 3) and 4) until a termination condition that the change amount of the cluster center gray scale values is smaller than an artificially set threshold value or iteration times are larger than some artificially set value; 6) completing initial superpixel division based on the finally obtained membership matrix; and 7) performing post-processing to complete the final superpixel division by combining sets of points ,which are isolated and unavoidably exist in superpixels generated after the above six steps, with adjacent superpixels which have the maximum similarity.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a superpixel segmentation method based on fuzzy theory. Background technique [0002] The so-called superpixel is to use a certain algorithm to aggregate certain pixel points together to form an atomic region with a certain perceptual meaning, which is used to replace the previous hard-segmented regional grid. Superpixels can effectively utilize spatial constraint information, have a certain degree of noise resistance, and retain the original boundary information of the image while strengthening the local consistency of the image. The atomic region segmented by the superpixel also contains some Image features, such as shape, boundary contour information, and regional grayscale histogram, are beneficial to improve the accuracy of image processing, and in terms of time complexity, superpixels are also greatly improved compared to single pixel processing. In addition, for the uneven...

AI Technical Summary

Problems solved by technology

The superpixels generated by the Quick-shift algorithm are not fixed in shape and quantity, and the compactness of the superpixels is also poor.

The most important point is that the current main superpixel segmentation methods are all aimed at natural images. When these methods are used to deal with medical images with specific fuzzy characteristics, the effect is often unsatisfactory. The segmented superpixels contain a variety of Medium, not conducive to further image processing

Images