Twin crystal boundary identification method, device and equipment and readable storage medium

Abstract

The invention discloses a twin crystal boundary identification method, device and equipment and a readable storage medium. The twin crystal boundary identification method comprises the following steps: acquiring a multi-crystal-grain image containing twin crystals; segmenting the multi-crystal-grain image by adopting a region growing algorithm based on pixel values to obtain a single-crystal-grain image; adopting a CLAHE method to adaptively enhance the single crystal grain image to obtain an enhanced single crystal grain image; performing multi-scale representation on the enhanced single crystal grain image by adopting a multi-scale image pyramid space representation method to obtain a single crystal grain image of each scale; detecting the single crystal grain image of each scale by adopting probability Hough transformation and a standard dynamic programming algorithm based on a Markov chain to obtain a plurality of straight line segments located on the crystal boundary of the twin crystal in the single crystal grain image of each scale; and carrying out adaptive combination and fusion on a plurality of straight line segments located on the twin crystal grain boundary in the single crystal grain image of each scale to obtain twin crystal grain boundary information in the single crystal grain image. According to the invention, the twin crystal boundary in the multi-crystal-grain image can be accurately identified.

Description

technical field [0001] The invention belongs to the cross field of material science and computer image digital processing technology, and specifically relates to a method, device, equipment and readable storage medium for identifying twin grain boundaries. Background technique [0002] With the development of society and the advancement of science and technology, the requirements for the reliability of advanced equipment are also increasing. As the basis for the development and application of modern advanced instruments and equipment, the performance of metal materials is directly related to the operational reliability of the equipment. Therefore, it is of great scientific significance and engineering value to improve and optimize them on the basis of existing metal materials. In the case of the same composition, the macroscopic properties of the material are directly related to the microstructure, and the crystal interface is one of the key structures that affect the macros...

AI Technical Summary

Problems solved by technology

The EBSD map contains a large amount of twin visual information, mainly twin grain boundaries. However, the feature extraction of twin crystal information at this stage still relies too much on human subjective feelings, and lacks a unified detection and measurement rule. Therefore, image digital processing is required. The means to analyze and detect the twinning information in the EBSD map

Relevant research and applications are limited by detection methods, and there are problems of limited accuracy caused by insufficient segmentation or excessive segmentation and limited accuracy caused by loss of detail information, and face the risk of being unable to continue in-depth exploration

Images