Overlaid fiber image segmentation method, device, storage medium and computer equipment

Abstract

The invention relates to a method, device, storage medium and computer equipment for overlapping fiber image segmentation. Feature points are extracted on the contour line of the contour image of overlapping fibers, and the feature points include concave points and convex points. For each concave point, find another concave point that matches the concave point, obtain two matching concave points, obtain a connecting line between the two matching concave points, and confirm that the connecting line is a dividing line. Segment the contour image of overlapping fibers according to the segmentation line to obtain the complete contour image of the segmented fibers. By looking for another matching concave point for each concave point in turn, two matching concave points are obtained, and the connection line between the two matched concave points is the dividing line of the contour image of the overlapping fiber, so that the overlapping can be paired according to the dividing line The contour image of the fiber is segmented to obtain a complete contour image of a single fiber. It solves the problem of low accuracy caused by subjective factors when identifying and counting overlapping fibers manually in the traditional way.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, device, storage medium and computer equipment for overlapping fiber image segmentation. Background technique [0002] my country is a big country in the production and export of textiles, and blended chemical fiber fabrics are a very important part of textiles. Blended chemical fiber fabrics are textiles made of chemical fibers mixed with other natural fibers such as cotton wool, silk, and hemp. For textile processing manufacturers and import and export manufacturers, the analysis of fiber content in blended chemical fiber fabrics is very important, and it is often necessary to carry out quantitative statistics and parameter measurement of fibers in blended chemical fiber fabrics. The traditional method of counting the number of fibers and measuring the parameters is done manually. When manually detecting and identifying fibers, subjective factors are often mi...

AI Technical Summary

Problems solved by technology

The traditional method of counting the number of fibers and measuring the parameters is done manually. When manually detecting and identifying fibers, subjective factors are often mixed, so the speed is slow and the error rate is high.

Images