Welding seam image identification method, computer device and computer readable storage medium

Abstract

The invention discloses a welding seam image identification method, a computer device and a computer readable storage medium. The method includes the steps: receiving image data, performing Gaussian filtering on the received image data, and performing binarization processing on the image data after Gaussian filtering; performing edge detection on an image after binarization, and calculating a structural light center line in the image after binarization; calculating an initial straight line model of a laser bar in the image after edge detection by the aid of a random sampling consistency algorithm, calculating an interest area based on the initial straight line model, calculating an accurate straight line model of a laser bar in the image in the interest area by the aid of the random sampling consistency algorithm again, and calculating an area of welding seam characteristic information in the interest area. The invention further provides a computer device for implementing the method and a computer readable storage medium. According to the method, the welding seam characteristic information in the image can be rapidly identified, and the identifying efficiency of welding seam characteristics is improved.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a recognition of weld seam images based on RANSAC algorithm, a computer device for realizing the method, and a computer-readable storage medium. Background technique [0002] Laser welding technology is widely used in the welding of electronic equipment. Because laser welding has the advantage of very fine weld seam, it is widely used in precision electronic equipment. However, since the weld seam of laser welding is very thin, it is difficult to observe with the naked eye in case of poor welding. At present, machines and equipment have been widely used to inspect the weld seam of laser welding. Usually, a camera device, such as a CCD sensor, is installed on the robot, and the camera device is used to take pictures and identify the pictures, so as to identify whether the weld seam is abnormal. [0003] Therefore, at present, machine vision technology has been widely used ...

AI Technical Summary

Problems solved by technology

Since the images before welding generally have regular-shaped grooves at the welding position, and the images after welding generally have different shapes, it is difficult to locate the characteristic position of the weld reinforcement, which increases the difficulty of image processing

Images