Method for automatic segmentation of defective image

Abstract

The invention discloses a method for automatic segmentation of a defective image. The method comprises the steps that A, image data are clustered through two-layer subtraction clustering; B, arrangement is conducted on center sets from big to small; C, a central point set V is initialized through first c elements; D, an efficiency analysis index of clustering is calculated; E, c=c+1 and an iterative computation is conducted until c>cmax; F, the value of V is determined when FXB (U,V,c) is the least value; G, U is calculated again through the value of V and image segmentation is conducted according to the formula that uik=max{u1k, u2k,...,uck} and xi belongs to the ith type. The method can overcome the shortages of the prior art, automatic segmentation in random walking mode is achieved, the image processing quality is improved, operation time is shortened, and the work efficiency is improved.

Description

technical field [0001] The present invention relates to the technical fields of graphics and image processing, pattern recognition and machine vision, in particular to an automatic segmentation method for defective images. Background technique [0002] With the wide application and rapid development of computer technology, graphics and image processing, pattern recognition and machine vision have gradually become popular research topics. So far, researchers have proposed thousands of image segmentation methods, and these methods have achieved certain results in varying degrees, but most of the research results are aimed at a certain type of image or for a specific application background. And design, there is no unified solution, specific analysis of specific problems, usually need to be combined with relevant domain knowledge to solve this type of image segmentation problem more effectively, due to the lack of a unified technical means to know how to perform appropriate segm...

AI Technical Summary

Problems solved by technology

So far, researchers have proposed thousands of image segmentation methods, and these methods have achieved certain results in varying degrees, but most of the research results are aimed at a certain type of image or for a specific application background. And design, there is no unified solution, specific analysis of specific problems, usually need to be combined with relevant domain knowledge to solve this type of image segmentation problem more effectively, due to the lack of a unified technical means to know how to perform appropriate segmentation based on the image Method design and selection

Therefore, image segmentation is still the most challenging problem in image processing and machine vision, which greatly restricts the development and application of this subject.

Images