A method for surface defect detection of mechanical parts based on image processing

Abstract

The invention relates to the technical field of image processing, in particular to a method for detecting surface defects of mechanical parts based on image processing. The method includes: collecting a surface image of a mechanical part under a standard light source, obtaining a segmented image of the surface image as a preliminary defect detection result; screening out the region to be detected in the segmented image, extracting connected domains and clustering the region to be detected, and obtaining multiple A set of regions to be detected; for each set of regions to be detected, move the light source, collect the second surface image, and obtain the characteristic information of the region to be detected in the second surface image; according to the characteristic information, the corresponding most significant defect is obtained Best light source; obtaining the best image of each region to be detected under the corresponding best light source to form a fused image, performing semantic segmentation on the fused image to obtain a second segmented image, and obtaining a detection result. The embodiments of the present invention can adaptively adjust the light source for different defects, and obtain accurate defect detection results.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting surface defects of mechanical parts based on image processing. Background technique [0002] During the production and processing of mechanical parts, defects will be generated on the surface of mechanical parts due to production equipment failure, raw materials mixed with sundries, and improper operation of operators. Defects have a great impact on the safe use of mechanical parts. In order to ensure the product quality, safety and life of mechanical parts in automatic production, it is an indispensable key link to detect defects on the surface of mechanical parts. [0003] Traditional automatic inspection methods are mostly based on machine vision technology, which collects surface images of parts and performs corresponding image processing to extract surface defects. However, the defect situation is often affected by the environment such as lig...

AI Technical Summary

Problems solved by technology

However, the defect situation is often affected by the environment such as lighting. It is difficult to comprehensively analyze surface defects only through image information, and sometimes even no defect information can be collected at all. The false positive rate and missed detection rate are relatively high.

Images