A method and system for detecting inter-line black foreign matter based on multi-channel differential gray scale analysis

By employing multi-channel differential grayscale analysis and morphological detection rules, the problem of difficult identification of black foreign objects between lines was solved, achieving efficient and accurate detection, improving detection precision and efficiency, and adapting to complex production line environments.

CN122175968APending Publication Date: 2026-06-09QINGHE ELECTRONIC TECH (SHANDONG) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
QINGHE ELECTRONIC TECH (SHANDONG) CO LTD
Filing Date
2026-05-07
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing automated optical inspection methods are ineffective at identifying black foreign objects between circuits, resulting in insufficient inspection capabilities, decreased product yield, and increased costs.

Method used

A multi-channel differential grayscale analysis method is adopted to obtain the blue spectral component of the circuit board, perform differential enhancement processing, configure multiple detection channels for parallel detection, combine morphological detection rules, dynamically calculate the substrate reference grayscale value, set sensitivity parameters, and generate a high-quality test report.

Benefits of technology

It improves the detection rate of black foreign objects between lines, reduces the false detection rate, enhances detection accuracy and efficiency, meets the needs of high-speed detection, adapts to different batches and lighting conditions, and improves the stability and traceability of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122175968A_ABST
    Figure CN122175968A_ABST
Patent Text Reader

Abstract

This application provides a method and system for detecting black foreign objects between circuit boards based on multi-channel differential grayscale analysis, belonging to the field of automatic optical inspection technology for semiconductor packaging substrates. The method involves: acquiring the original image of the circuit board under test under a preset light source; extracting spectral components within a preset wavelength range to generate an image to be processed; and performing differential enhancement processing to generate an enhanced image. According to a preset scanning strategy, the effective detection area image is extracted from the enhanced image, and the reference grayscale value of the substrate is calculated. At least two detection channels are configured, with different grayscale threshold ranges and detection targets set for each channel. The effective detection area image is input into each of the at least two detection channels, and defect detection is performed in parallel based on the grayscale threshold ranges set for each channel. The detection results from each detection channel are then combined to output the final defect information. This application utilizes multi-channel differential grayscale analysis to enhance contrast, accurately identify black foreign objects, and reduce false alarms.
Need to check novelty before this filing date? Find Prior Art