Deep learning-based packaged chip defect detection method

Abstract

The invention discloses a deep learning-based packaged chip defect detection method. The method comprises the following steps: carrying out noise reduction processing on an X-ray image of a packaged chip; performing image segmentation on the X-ray image, and extracting a test image with a packaged chip; obtaining inner and outer edges of a sealing ring of the chip in the test image based on template matching; establishing a training data set and a target detection model, and training a target detection network; detecting the test image based on the trained target detection model to obtain a detection frame corresponding to a defect area in the test image; performing fine positioning correction on the detection frame based on region growth; and carrying out qualification judgment on the chip based on the shortest path between the inner and outer edges of the sealing ring and the detection frame. A computer vision technology represented by a deep learning vision detection technology is deeply studied, an electronic component X-ray inspection bubble defect automatic identification method is developed, and the urgent demand of military electronic component quality detection is met.

Description

technical field [0001] The present invention relates to the field of package chip defect detection / image processing technology field, in particular to a package chip defect detection method based on deep learning. Background technique [0002] Traditional artificial visual inspection, automatic optical inspection and other inspection technologies are almost powerless to the internal quality inspection of components. The X-ray inspection method uses the transmission principle to perform X-ray imaging on electronic components, and the images can reflect the internal defects of electronic components. The inspectors browse the X-ray images, and perform manual interpretation and analysis according to the inspection standards. This manual interpretation and analysis method is affected by subjective factors such as worker experience and physical condition. The detection efficiency and reliability are low, and it is difficult to effectively guarantee the quality of component detecti...

AI Technical Summary

Problems solved by technology

This manual interpretation and analysis method is affected by subjective factors such as worker experience and physical condition. The detection efficiency and reliability are low, and it is difficult to effectively guarantee the quality of component detection, which brings risks and hidden dangers to the use of components. increasing demand

Images