A defect detection method for plastic package IC chips based on feature template matching and deep learning

A technology of deep learning and feature templates, which is applied in the direction of optical testing flaws/defects, measuring devices, scientific instruments, etc., and can solve problems such as defect identification, low accuracy of defect classification, and unclear printing information of pin chips

Active Publication Date: 2020-11-24
JIANGSU POLYTECHNIC COLLEGE OF AGRI & FORESTRY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A defect detection method for plastic package IC chips based on feature template matching and deep learning
  • A defect detection method for plastic package IC chips based on feature template matching and deep learning
  • A defect detection method for plastic package IC chips based on feature template matching and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] like figure 1 As shown, a method for defect detection of plastic encapsulated IC chips based on feature template matching and deep learning includes the following steps:

[0052] (1) Image acquisition and preprocessing

[0053] The IC chip image in the high-speed feeder is collected by a high frame rate CCD camera, and the image is preprocessed. First of all, in order to improve the quality of image acquisition, the red LED light source is fixed directly below the camera, such as figure 2 shown. Then, image filtering is performed on the collected target image to remove the noise signal existing in the image. Finally, a grayscale enhancement algorithm is used to improve the contrast of the image.

[0054] (2) Establish IC chip positioning template and character positioning template

[0055] The establishment of the IC chip positioning template and the character positioning template of the present invention is to use the edge detection method to locate the edge poin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/88
CPCG01N21/8851G01N2021/8854
Inventor 崔明周伟仲瑶吴燕
Owner JIANGSU POLYTECHNIC COLLEGE OF AGRI & FORESTRY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap