Image over-segmenting optimization method based on multi-target evolution clustering and spatial information

Abstract

The invention relates to an image overdivided optimization method based on multi-object evolutionary clustering and space information for applying the space information of the multi-object evolutionary clustering algorithm to the image overdivided optimization which includes steps as follows: (1) processing watershed pre-divide to an input image for obtaining overdivided result image; (2) statingcharacteristic of each area in the overdivided result image as data of the multi-object evolutionary clustering; (3) actualizing the multi-object evolutionary clustering, optimizing an object function added the space information by using the multi-object evolutionary clustering method, processing clustering to each area characteristic of the overdivided result image for obtaining a non-dominated solution set; (4) integrating the non-dominated solution set for obtaining final solution; (5) outputting the optimization result of the overdivided image according with final solution. The method introduces the multi-object evolutionary algorithm into the image dividing field for making the image clustering dividing method more stably and having better adaptability; the method uses the image space information that makes the image optimization dividing inner is more compact.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to the application of the technology in the field of image segmentation, in particular to an image segmentation method based on multi-objective evolutionary clustering and image space information, that is, S-MOCO. The method can be used in the technical field of image segmentation. Background technique [0002] Image segmentation is the basis of image understanding and pattern recognition. It is widely used in medicine, military, meteorology, climate, environment and other fields. It is a hot and difficult point in current research. So far, researchers have proposed many image segmentation methods, which can be roughly divided into the following three categories: region-based image segmentation, edge-based image segmentation and threshold-based segmentation methods. Watershed transform is a commonly used region-based image segmentation algorithm, which has the advantages of ...

AI Technical Summary

Problems solved by technology

For many practical multi-objective optimization problems, there are often great differences between different objectives in the multi-objective algorithm, and even incompatible characteristics. less than optimal result

Images