Automated Quality Control of Ceramic Inserts Using Vision Systems and Deep Neural Networks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The article presents a modular, automated inspection system for ceramic inserts used in DPF and GPF filters. The system integrates 3D scanning based on structured light with 2D imaging using telecentric optics. The applied hybrid detection algorithms, combining deep neural networks with classical image processing methods, enable the identification of cell blockage within the ceramic insert as well as defects on its external surface. Converting point clouds into 2D representations allows for the effective use of convolutional neural networks, simplifies the defect labeling process on images, and reduces computational requirements. The conducted tests confirmed high detection accuracy while maintaining short inspection times consistent with industrial constraints. The modular architecture and full automation of the inspection process enable flexible adaptation of the system to diverse production lines.
Fields of Study & Subjects
Industrial Vision Systems and Defect Detection
Non-Destructive Testing Techniques
Image Processing Techniques and Applications
Publication details
- Journal / source
- Pomiary, Automatyka, Robotyka
- Volume
- 30
- Issue
- 1
- Pages
- 127–134
- Publication date
- 27 March 2026
- Language
- EN