A wafer frame detection method, device, equipment and storage medium

By identifying target wafers and defects in wafer images, zeroing the grayscale value of defect areas, and adjusting the target bounding box by combining overall and local grayscale values, the detection accuracy problem of existing models under extreme conditions is solved, achieving higher precision and adaptive wafer bounding box detection.

CN117893835BActive Publication Date: 2026-07-21STORAGEX TECH INC
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STORAGEX TECH INC
Filing Date
2024-03-05
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing deep learning-based wafer edge detection models are prone to false positives or false negatives when there is a lack of large amounts of labeled data, extreme lighting, or occlusion. They also have high computational resource requirements, poor model interpretability, and limited generalization ability to unknown patterns, resulting in low detection accuracy.

Method used

By identifying the target wafer and defects in the wafer image, zeroing the grayscale value of the defect area, calculating the average grayscale value of the target wafer and the border, and adjusting the target box based on the grayscale value, a modified box is generated. Taking into account overall and local grayscale information, the target box is dynamically adjusted to improve detection accuracy.

Benefits of technology

It improves the accuracy and adaptability of wafer edge detection, enhances adaptability to different regions, reduces interference from defects in detection, and improves the accuracy and stability of edge recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117893835B_ABST
    Figure CN117893835B_ABST
Patent Text Reader

Abstract

The application relates to a wafer frame detection method, device and equipment and a storage medium, and is applied to the field of industrial detection optimization. The method comprises the following steps: obtaining a wafer picture, identifying a target wafer in the wafer picture and a target frame corresponding to the target wafer; identifying defects in the target wafer, and setting the gray value of the region where the defects are located to zero; calculating a first average gray value of the region where the target wafer is located; extracting a plurality of target edges corresponding to the target frame, and calculating a second average gray value of the region where the target edges are located; adjusting the target frame by combining the first average gray value and the second average gray value, and generating a modified frame. The application has the technical effect that multi-level gray information is comprehensively utilized, which is helpful to more comprehensively and accurately describe the characteristics of the wafer frame; not only the gray information of the target wafer as a whole is considered, but also the local gray information of the target edges is considered, the adaptability to different regions is improved, and the accuracy of frame detection is enhanced.
Need to check novelty before this filing date? Find Prior Art