Segmentation method for adhering grain binary image

Abstract

The invention relates to the technical field of complex grain image segmentation, in particular to a segmentation method for an adhering grain binary image. The segmentation method comprises the following steps: 1, extracting a skeleton of a target object for a binary area target; step 2, defining a boundary distance function of the skeleton in an Euclidean space; step 3, figuring out a minimum point, namely valley point, of the boundary distance function of the skeleton; and 4, taking the valley point as a center to segment the target object according to the minimum difference quotient of the area boundary distance function. The method provided by the invention facilitates segmentation of an adhering target area object in a binary image and has good antijamming capability.

Description

technical field [0001] The invention relates to the technical field of complex particle image segmentation, in particular to a method for segmenting a binary image of cohesive particles. Background technique [0002] Image segmentation algorithm is a basic method of image processing. It is the first problem to be solved in image analysis and pattern recognition. Its fundamental purpose is to separate valuable regions from the background. Using the "quality" characteristics of the image, people have proposed various algorithms, which can be roughly divided into the following categories: gray threshold method, region growing method, edge detection method, loose method and so on. These methods all rely on grayscale or color similarities or discontinuities in images. Affected by noise or the interconnection of regional objects themselves, in the image segmentation results of the above algorithm, there will always be some regions gathered together, that is, multiple objects are ...

AI Technical Summary

Problems solved by technology

This method is intuitive and simple, but in actual processing, the adhesion of regional objects is different, and the pairing of pit points is complicated, so the algorithms have the following problems to varying degrees:

The polygon approximation algorithm blurs the concave-convex features of the area object to a certain extent, and is easily affected by noise, thus affecting the correct calculation of concave points

Segmenting the area object with the wrong concave point will inevitably cause the segmentation to fail

[0006] (2) It is difficult to match the concave points

[0007] (3) It is difficult to find the separation point set or separation curve

The algorithm can better segment objects under the premise that the local gray level changes are more obvious, but when the illumination causes uneven gray level changes, the algorithm is powerless, which also leads to segmentation failure

Images