A method of workpiece defect detection based on machine vision

Abstract

The invention discloses a workpiece defect detection method based on machine vision. The workpiece defect detection method comprises the following steps: reading a template workpiece image and images of a workpiece to be detected; performing rough matching on the images of the workpiece to be detected and the template workpiece image, so as to obtain an image with the highest matching degree with the template workpiece image; partitioning same areas of the image of the workpiece to be detected after modification and the original template workpiece image, and performing fine matching on each subarea after partitioning; comparing each subarea image of the workpiece to be detected after modification with corresponding subarea images of the template workpiece image, analyzing, finding defects, and acquiring final defect detection results of each subarea; marking the defect detection results of each subarea on the template workpiece image, and outputting template images with defect markers. By adopting the workpiece defect detection method, high-precision matching of multiple types of workpieces to be detected with template workpiece images can be met, and a relatively high accuracy rate can be achieved in defect detection.

Description

Technical field [0001] The invention relates to a machine vision intelligent detection method, in particular to a machine vision-based method for detecting defects of automobile fuse box workpieces. Background technique [0002] Product testing is an indispensable part of industrial production and plays an important role in improving product quality. Under normal circumstances, industrially manufactured workpieces have a certain defective rate. The traditional method is to manually inspect the workpieces. On the one hand, the efficiency of workpiece shipment is low, and the accuracy rate is also difficult to guarantee. On the other hand, it increases the overall quality of the workpiece. Processing cost affects production efficiency. Modern industry pays attention to online, real-time, fast and non-contact detection methods to improve product production efficiency under the premise of ensuring product quality. [0003] The quality of the car fuse box plays a vital role in the saf...

AI Technical Summary

Problems solved by technology

At present, the method of manual detection of defects in automobile fuse boxes has the disadvantages of low efficiency and high cost. An automatic detection system for defects in automobile fuse boxes is urgently needed to quickly and accurately screen out unqualified products, improve production efficiency, and reduce potential safety hazards.

At the same time, due to the complex internal structure of the automobile fuse box, the main defect types of the workpiece are more glue and less glue, and the defects are small and inconspicuous, which greatly increases the difficulty of manual inspection. The average inspection time of each workpiece is 5 minutes, resulting in the actual output is not high

Images