A metallographic image edge detection method based on mathematical morphology

Abstract

The invention discloses a metallographic image edge detection method based on mathematical morphology. Firstly, the metallographic image is converted into a contrast-equalized gray-scale image to reduce noise and enhance edge information. Then the histogram of the image is computed, the histogram is normalized, the integrals of the histogram are computed, and the integrals of the histogram are used as a look-up table for image transformation. Secondly, two thresholds of segmented images are generated by a self-defined improved algorithm based on iterative method. The foreground image and background image of the image are segmented by the two thresholds respectively. NAND operation is performed on the two images to remove the grains-independent structures from the images. Finally, the edgeimage of the grain is obtained by the self-defined multi-scale and multi-structure algorithm. The invention reduces the boundaries of missed detection, multiple detection and false detection, the extracted edges have better continuity and smoothness, and the positioning of the boundaries is more accurate, and the characteristics of the metallographic images are fully considered, so that the pertinence is stronger.

Description

technical field [0001] The invention belongs to the technical field of image processing or computer vision, in particular to a metallographic image edge detection method based on mathematical morphology. Background technique [0002] As a comprehensive subject, metallography research mainly includes the following three contents: Basic theoretical research: mainly involves the application of mathematical methods such as stereology principles, geometry, topology, probability theory and mathematical statistics; testing methods and equipment instruments Research: mainly includes image processing and testing technology calculation programs and error analysis, etc.; applied research: mainly includes all aspects of theoretical research in materials science and automatic inspection and control of material production processes. [0003] At present, in quantitative metallography, scholars at home and abroad have done a lot of research on metallographic image processing technology, and...

AI Technical Summary

Problems solved by technology

Commonly used traditional edge detection algorithms include: first-order differential edge detection operators include Robert gradient operator, Sobel operator, Prewitt operator, etc. These operators are sensitive to noise and have poor noise resistance. It will strengthen the noise, and the amount of calculation is relatively large

The operators of the second-order differential edge detection include Laplacian operator, Kirsh operator, Walks operator and other nonlinear operators. This kind of operator is similar to high-pass filter, which has the function of enhancing high-frequency components. Therefore, for noise More sensitive; especially the Laplacian operator is very sensitive to the noise in the metallographic image and cannot correctly extract image edge information

[0004] In short, the disadvantages of these traditional edge detection algorithms applied to metallographic images are as follows: 1) the accuracy of edge detection is not high, and cannot fully express the details of edge detection in metallographic images; 2) the anti-noise ability is poor, and metallographic images There is a lot of noise in it, which seriously affects the quality of edge detection; 3) The amount of calculation is large, and the operation time is relatively long

Images