Segmentation method of weld defect images

Abstract

The invention discloses a segmentation method for weld defect images. The segmentation method for weld defect images comprises the steps: aftering pre-processing an image, performing gray curve fitting on each column of pixel points on the image to obtain a gray curve; extracting the minimum points on the curve, and determing the size of the structural element is determined according to the corresponding characteristics of the minimum points; simulating the background image of the weld by the closed operation in morphology, and extracting the defect image of the weld by digital subtraction technology. The segmentation method of the weld defect image can effectively solve the problem that it is difficult to extract the defect part of the weld image due to the texture complexity of the weldimage, realizes more reliable, more accurate and more universal segmentation and extraction of the welding seam defect image, and is conducive to realizing automatic detection of the weldi defect image.

Description

technical field [0001] The invention relates to image defect segmentation technology, in particular to a method for segmenting weld seam defect images. Background technique [0002] Traditional welding defect detection methods mainly rely on manual judgment of welding digital images (such as X-ray welding images or ultrasonic welding images, etc.), which have problems of low efficiency and high false detection rate. With the development of image processing technology, defect detection on digital welding images has become an important means of quality evaluation of welding products. Welding digital images usually have low contrast, large background fluctuations, and a small amount of noise, which can easily cause missed and misjudged defects. [0003] In the traditional method, the detection of welding defects mainly includes four processes. The first process is image acquisition. The second process is image preprocessing, which is mainly divided into two parts: image nois...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome that the image defect segmentation method used in the prior art for welding defect detection is prone to errors, the extracted defect edge is too rough, the segmentation result is easily disturbed by noise, the reliability of the segmentation effect is insufficient, and the general In order to solve the problem of insufficient adaptability, a segmentation method for weld defect images is proposed

Images