A method and system for detecting ring varistor based on image feature extraction

By constructing a radial reference brightness model and Weber contrast features, and combining fuzzy C-means clustering and spatial constraint strength, the material reflectivity differences on the surface of the annular varistor are adaptively eliminated, solving the problems of missed detection and misjudgment in optical detection, and improving detection accuracy and robustness.

CN122134631APending Publication Date: 2026-06-02DONGGUAN E-LEO ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
DONGGUAN E-LEO ELECTRONICS CO LTD
Filing Date
2026-01-29
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing automated optical inspection methods suffer from problems such as missed detection and misjudgment due to uneven illumination and differences in material reflectivity in the detection of surface defects of ring varistors, making it difficult to effectively balance noise reduction and edge preservation.

Method used

By constructing a radial reference brightness model and Weber contrast features, combined with fuzzy C-means clustering and spatial constraint strength, the material reflectivity difference is adaptively eliminated, and the pixel membership degree is corrected using neighborhood information to achieve defect detection.

Benefits of technology

It significantly improves the robustness and accuracy of surface defect detection of ring varistors, effectively removes reflective noise, preserves defect edge details, and reduces the false detection rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122134631A_ABST
    Figure CN122134631A_ABST
Patent Text Reader

Abstract

This application relates to the field of image processing technology, and in particular to a method and system for detecting ring-shaped varistors based on image feature extraction. The method includes: acquiring a grayscale image of the ring-shaped varistor and determining the center of the image circle; statistically analyzing the pixel grayscale distribution at different radii to construct a radial reference brightness model; comparing the grayscale values ​​of the pixels with the radial reference brightness model to obtain a contrast feature map; calculating the initial membership degree of the pixels belonging to the defect category; calculating the spatial constraint strength of the pixels; correcting the initial membership degree of the pixels using the spatial constraint strength and the initial membership degree of neighboring pixels to obtain the target membership degree; and obtaining the defect detection result based on the target membership degree. The technical solution of this application can improve the robustness and detection accuracy of surface defect detection of ring-shaped varistors.
Need to check novelty before this filing date? Find Prior Art