Method for detecting package IC (Integrated Circuit) chip defects based on feature template matching and in-depth learning

Abstract

The invention discloses a method for detecting package IC (Integrated Circuit) chip defects based on feature template matching and in-depth learning. The method comprises the following steps: (1) image acquisition and preprocessing; (2) establishing an IC chip positioning template and a character positioning template; (3) performing chip positioning and character detection based on feature template matching; (4) character defect determination; (5) creating and training a convolutional neural network in-depth learning framework; and (6) detecting and classifying IC pin chip defects. The methoddisclosed by the invention can achieve effects of effectively detecting character defects of IC chips in the package body and completing defect classification of the pins, has high accuracy rate, andcan meet online detection requirements of the IC chips in the package body.

Description

technical field [0001] The invention relates to the technical fields of image processing and artificial intelligence, in particular to a defect detection method for plastic encapsulated IC chips based on feature template matching and deep learning. Background technique [0002] With the rapid development of the electronics industry, the demand for IC chips is increasing, and chip testing has become an indispensable link in the electronics industry. Traditional manual inspection methods are not only inefficient, but also costly. Applying machine vision technology to the field of industrial inspection not only improves the quality of products, but also improves the efficiency of industrial production. Nowadays, image processing technology has been widely used in the field of industrial production, realizing high-precision detection and positioning of products. [0003] At this stage, research on visual inspection of IC chips has made great progress. In 2008, Hawari et al. p...

AI Technical Summary

Problems solved by technology

[0004] Although many research results have been obtained on IC chip surface defect detection, there are still relatively few domestic related research work on real-time high-speed high-precision detection and positioning in the IC post-production process, especially on pin defects, chip defects, etc. The technology for problems such as unclear printing information is still immature, and the research on defect classification is still in the identification of obvious defects, and the accuracy of defect classification is low

Images