Image segmentation method based on multi-granularity genetic algorithm

Abstract

The invention discloses an image segmentation method based on a multi-granularity genetic algorithm, and relates to the field of image processing. The method comprises the following steps: firstly, taking maximization of an inter-class variance and the like as targets to obtain a fitness function for evaluating image segmentation performance; and then, according to the fitness function for evaluating the image segmentation performance, searching through a multi-granularity genetic algorithm to obtain an optimal threshold; when the optimal solution changes, introducing a layering strategy intothe multi-granularity genetic algorithm, performing genetic operation according to the layering situation, introducing a multi-granularity space strategy to divide a feasible region, achieving randomsampling in a sparse space and a subspace where the current optimal solution is located, and migrating the subspace to a current population to replace individuals with poor fitness values in the population. According to the multi-granularity genetic algorithm, the search intensity of the sparse space and the subspace where the current optimal solution is located is improved, and the searched approximate optimal solution is promoted to be more effectively close to the global optimal solution, so that the optimal image segmentation threshold is obtained, and the purpose of improving the image segmentation precision is achieved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for finding an optimal threshold in image segmentation. Background technique [0002] Image segmentation is the first step in image analysis. The quality of subsequent tasks of image segmentation depends on the quality of image segmentation, such as feature extraction and target recognition. Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. From a mathematical point of view, image segmentation is the process of dividing a digital image into mutually disjoint regions. These regions are mutually disjoint, and each region satisfies a certain similarity criterion of features such as grayscale, texture, and color. The threshold-based segmentation method is a common method of image segmentation, which uses one or several thresholds to divide the gray histogram of the im...

AI Technical Summary

Problems solved by technology

Therefore, the genetic algorithm is easy to fall into local optimum and other shortcomings, so that the obtained threshold may not be the global optimal threshold, thus affecting the performance of image segmentation.

Images