A multi-target fast fuzzy clustering color image segmentation method based on semi-supervised learning and histogram statistics

Abstract

The invention discloses a multi-target fast fuzzy clustering color image segmentation method based on semi-supervised learning and histogram statistics. The method comprises the following steps: inputting a color image to be segmented; Setting an initial population number of the color image, the Maximum number of iterations, and the Maximum clustering number, obtaining paired constraint information given by a user and processing the paired constraint information to obtain paired constraint matrixes; obtaining a color histogram according to the color image; based on the Color histogram, constructing a fitness function of intra-class compactness based on paired constraint and inter-class separability based on clustering inpurity; secondly, designing self-adjusting crossover and variation rate, utilizing mixed crossover and non-uniform variation to generate filial generations so as to ensure the diversity of the filial generations, finally constructing clustering non-purity effectivenessindexes based on color histograms, selecting an optimal solution from an optimal solution set, and obtaining a final segmentation result. According to the method, under the condition that a small amount of paired constraint information is used, rapid segmentation can be achieved, and the segmentation number and the good segmentation effect are obtained in a self-adaptive mode.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-objective fast fuzzy clustering color image segmentation method based on semi-supervised learning and histogram statistics. Background technique [0002] Image segmentation is an important part of the image processing process. It divides the image into several different regions. The features in the same region are consistent, which is helpful for the extraction of objects of interest. The quality of image segmentation directly affects the follow-up process of image processing, so people pay more and more attention to it. In recent years, as the computer's ability to process data has been greatly improved, the research on color image segmentation technology has attracted the attention and attention of scholars at home and abroad. At present, we can divide color image segmentation algorithms into threshold-based, edge-based, region-based and cluster-based segmenta...

AI Technical Summary

Problems solved by technology

In 2005, Grirs et al. effectively combined the semi-supervised clustering method with the competitive algorithm and proposed the active fuzzy-limited clustering algorithm. Although the performance of the traditional clustering algorithm was improved, there were clustering problems for color images with many colors. The problem with too many categories

In 2017, Wang Jun et al. proposed a multi-objective evolutionary fuzzy clustering algorithm based on category label information, which introduced category label information as supervisory information into the multi-objective evolutionary fuzzy clustering algorithm to guide clustering to obtain a more ideal clustering algorithm. Segmentation results, but the use of supervision information is not comprehensive enough, only the supervision information is introduced into an objective function, and the class label information used is not easy to obtain in life

Images