Gypsum board defect detection method and system based on bidirectional structured light
By combining bidirectional structured light and twin neural networks in gypsum board production, the randomness problem caused by unidirectional laser detection is solved, defect detection with higher accuracy and robustness is achieved, costs are reduced and detection efficiency is improved.
Patent Information
- Application Number
- CN202510789450.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-13
- Publication Date
- 2025-09-23
AI Technical Summary
The existing gypsum board defect detection system uses unidirectional laser detection, which results in unconstrained detection image features, strong detection randomness, and reduced detection accuracy.
A method combining bidirectional structured light and twin neural networks is adopted. Structured light is emitted from both sides of the gypsum board at a preset angle using a structured light emitter. Bidirectional detection images are collected using a high-speed industrial camera. Image recognition training is performed using the twin neural network. A defect detection network is constructed and defect recognition is performed in combination with a classifier.
The accuracy and robustness of defect detection are improved, detection errors are reduced, costs are reduced, detection efficiency is improved, and external environmental interference is avoided.