Small-size chip crack detection method and system based on computer vision

Abstract

The invention provides a small-size chip crack detection method and system based on computer vision. The method comprises the steps that a to-be-detected image of a small-size chip is acquired; performing median filtering on the to-be-detected image; gray scale transformation enhancement is carried out on the to-be-detected image; performing image segmentation on the to-be-detected image through amaximum between-cluster variance method to obtain a binary image; connected domain marking is carried out on the binary image to acquire a pixel point set of the defect area; and judging whether thedefect area is a crack defect or not according to the area, the gravity center, the long axis, the short axis and the gray value of the defect area. Whether the defect area is a crack or not is judgeddirectly through the area, the gravity center, the long axis, the short axis and the gray value of the defect area; according to the method, registration and position correction of the to-be-detectedimage and the standard image are not needed, crack defects in various defects do not need to be further recognized, the calculation process and the calculation amount are greatly simplified, introduced noise interference is reduced, and the reliability of the detection result is improved.

Description

technical field [0001] The invention relates to the field of AOI technology, in particular to a computer vision-based small-size chip crack detection method and system. Background technique [0002] Since entering the 21st century, the electronic technology industry has developed particularly rapidly. The development of components in the electronic assembly industry has been developing in-depth towards miniaturization, functionalization, modularization, and integration of production design. At this time, manual visual inspection alone can no longer meet the reliable and consistent inspection objectives, not to mention the desire to preserve accurate information, which has prompted manufacturers to install automatic optical inspection systems (Automatic Optical Inspection, referred to as AOI) for their production lines. ). AOI is often used in the defect detection of small-sized chips. First, the chip is converted into image data by using the image acquisition system and tra...

AI Technical Summary

Problems solved by technology

[0004] In view of this, on the one hand, the present invention proposes a small-size chip crack detection method based on computer vision to solve the problem that the traditional small-size chip AOI detection method is complex in the detection process due to image position correction and defect extraction, and introduces noise interference. Direct and easy identification of chip crack problems

Images