一种鞋中底毛边缺陷检测方法、系统、介质及设备
By employing adaptive illumination preprocessing, an improved YOLOv8-seg model, and morphological postprocessing, the problems of low efficiency, inconsistent standards, and poor adaptability in the detection of burr defects in shoe midsoles have been solved, achieving efficient and stable automated detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SOUTH CHINA UNIV OF TECH
- Filing Date
- 2026-03-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are inefficient, lack standardized procedures, and have poor adaptability in detecting burr defects in shoe midsoles. They are also sensitive to changes in lighting and appearance, leading to unstable test results.
By employing a deep learning-based approach, combined with adaptive OTSU threshold segmentation and illumination correction preprocessing, improved YOLOv8-seg model detection, and morphological postprocessing, we can achieve the detection of rough edges on shoe midsoles with different designs.
It achieves robust, accurate, and automated detection of burr defects in shoe midsoles with different appearance designs, reduces sensitivity to light and appearance changes, and improves detection efficiency and consistency.
Smart Images
Figure CN122415449A_ABST