Defect quantitative evaluation method based on AOI detection

Abstract

The invention relates to the technical field of AOI defect detection, and discloses an AOI-detection-based defect quantitative evaluation method, which comprises the following steps: S1, defect separation: on a detected defect picture, according to the area where the defect is located, the defect is separated from a background picture by using the steps of noise removal, gray stretching, filtering and image difference before and after filtering, the width of the minimum bounding rectangle is calculated according to the contour of the flaw, and the separated flaw graph and the bounding rectangle block diagram where the flaw is located are respectively stored. According to the AOI detection-based flaw quantitative evaluation method, the functions of appearance flaw quantitative evaluation and automatic detection can be realized, manual judgment through subjective experience is not needed, subjective factor interference is avoided as much as possible, the accuracy of a flaw detection result is improved, the flaw detection efficiency is also improved, and the labor intensity of workers is reduced.

Description

technical field [0001] The invention relates to the technical field of AOI defect detection, in particular to a defect quantitative evaluation method based on AOI detection. Background technique [0002] The full name of AOI in Chinese is Automatic Optical Inspection, which is based on the optical principle to detect common defects encountered in welding production. Comparing the qualified parameters, after image processing, the defects on the PCB are checked out, and the defects are displayed / marked through the display or automatic signs for repairing by maintenance personnel. [0003] At present, in the field of AOI defect detection, the detected defects are large or small. As for whether each defect will affect the product function and performance, and whether the corresponding defect is within the acceptable range, there is no quantitative evaluation method, which must be manually passed. Subjective experience is used to judge which defects are acceptable, but there are...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a defect quantitative evaluation method based on AOI detection, which can realize the functions of quantitative evaluation and automatic detection of appearance defects, without relying on manual judgment through subjective experience, and avoiding the interference of subjective factors as much as possible, not only The accuracy of the defect detection result is improved, the efficiency of the defect detection is also improved, and the labor intensity of the staff is reduced. Manual operation also has the problem of low defect detection efficiency

Images