Welding identification method for automobile parts

Abstract

The invention relates to a welding identification method for an automobile part, and belongs to the technical field of identifying a welding seam by using a computer vision technology, and the method comprises the following steps: obtaining a first side neighborhood and a second side neighborhood of each independent contour line in an automobile part image; when the color richness of the neighborhood of any side in any independent contour line is larger than a color richness threshold value, the independent contour line serves as an alternative weld line; selecting a to-be-determined weld line from the alternative weld lines by using the color contrast of the neighborhoods on the two sides of each alternative weld line and the texture contrast of the neighborhoods on the two sides of each alternative weld line; carrying out wrapping detection on any two to-be-determined weld lines to identify a final weld line, and taking an area surrounded in the final weld line as a welding area; according to the method for identifying the welding area of the automobile part based on the welding area characteristics and the morphological structure characteristics of the area around the welding area, the false detection rate of the welding area is greatly reduced.

Description

technical field [0001] The invention belongs to the technical field of using computer vision technology to identify welding seams, and particularly relates to a welding identification method for automobile parts. Background technique [0002] Auto parts are various parts that make up the whole car. There are many kinds of auto parts. The quality of auto parts plays a great role in the quality of the whole vehicle and is one of the key elements of the quality of the whole vehicle. In order to ensure the quality of auto parts, higher requirements are also put forward for the welding of auto parts. The quality of welding directly affects the quality of auto parts, and it is necessary to quickly extract the weld area when testing the welding quality. . [0003] At present, with the rapid development of artificial intelligence technology, how to use computer vision technology to quickly identify the weld area is the first technical problem to be solved. However, due to the gene...

AI Technical Summary

Problems solved by technology

However, because the general structure of auto parts is relatively complex, there are edge lines that are difficult to distinguish. At the same time, the metal on the surface of auto parts will have reflective areas that are difficult to distinguish from bright welding areas, and the surface of auto parts will also appear similar to the welding area. Pore ​​structure, which brings difficulties to the extraction of welded areas

Images