Goldfinger image construction method and goldfinger defect detection method

By identifying and distinguishing the outline of the gold finger, generating a collection of standard sequence diagrams of the gold fingers, and performing splicing processing, the problem of low detection accuracy of gold finger defects is solved, and efficient and accurate defect detection is achieved.

CN119206302BActive Publication Date: 2025-03-25SHANGHAI GANTU NETWORK TECHNOLOGY CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202411195946.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2025-03-25
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

In the prior art, the instability of optical schemes and visual detection equipment leads to low detection accuracy of gold finger defects, and manual detection affects the production line detection interest rate.

Method used

By obtaining a panoramic view of the standard material board, identifying the outline of the gold finger, distinguishing the type of the gold finger, generating a collection of standard sequence diagrams of the gold fingers, and based on this, the splicing and defect detection of the gold fingers to be sequenced are carried out.

Benefits of technology

The accuracy of gold finger defect detection is improved, the problem of insufficient detection caused by chromatic aberration is avoided, and efficient defect detection is achieved through non-AI recognition.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application discloses a gold finger image construction method and a gold finger defect detection method, which relates to the field of AOI image detection, obtains a panoramic image of a standard material board, identifies all gold finger contours in the standard material board, and distinguishes the gold finger types based on the gold finger contour features; generates a gold finger thumbnail corresponding to each gold finger contour, performs image splicing processing on the same type of gold finger thumbnails according to preset puzzle rules, generates a gold finger standard sequence diagram set, and also obtains a gold finger index to-be-tested diagram set of the material board to be tested in the material running stage, detects gold finger defects in the gold finger to-be-sequenced diagram set based on the gold finger standard sequence diagram set, and converts the gold finger defects detected in the gold finger to-be-sequenced diagram to the panoramic image of the material board to be tested, and obtains the gold finger defect distribution. This solution uses image modeling and segmentation matching methods for defect detection, which is more accurate than traditional AI recognition and avoids the problem of insufficient detection due to color difference.
Need to check novelty before this filing date? Find Prior Art