Industrial defect detection method and system

Abstract

The invention discloses an industrial defect detection method and system. The system comprises a receiving module, a detection module, a sorting module, a performance analysis module, a post-processing module and a visualization module, the method comprises the following steps: initializing a system: respectively initializing a detection model and a sorting model; inputting a picture, verifying the picture, and rejecting a bad picture to obtain a to-be-detected image; counting the current system performance and the system resource occupation condition of the current process in real time according to the number of input to-be-detected images, and adjusting the thread count of a detection module; positioning the defect area of the to-be-detected image by adopting a shape matching positioning mode; then, the pictures are sorted through traditional edge detection, a dynamic threshold value, a classification model combined with deep learning and the like, and defect types are sorted out; and statistical analysis is carried out on the sorted result, and then the final result is visualized. According to the invention, the detection rate of industrial defect detection can be improved.

Description

technical field [0001] The present invention relates to the field of image processing, and more specifically, to an industrial defect detection method and system. Background technique [0002] In the actual industrial production process, due to the influence of the manufacturing process and other factors, defects such as foreign matter, missing chips, black spots, crystal points, scratches, spots, etc. will appear on the surface of wafers, packages, and PCBs. These defects will seriously affect The quality and lifespan of the electronic chip are reduced, and it also brings great economic losses to the manufacturer. [0003] There are many kinds of industrial defects, such as missing gold wires, bad gold wires, bent gold wires, excess glue, less glue, solder leakage, poor solid crystal, and cracked crystals, etc., and the defects are often small in size, such as those with a diameter of less than 0.02mm. Dirty spots, streaks, tears, edge cracks, wrinkles, edge damage, black ...

AI Technical Summary

Problems solved by technology

Since chip products are often updated and iterated relatively quickly, this solution has the dilemma of slow file building

Images