Row-level algorithm to improve real-time performance of glass tube defect detection in the production phase
| Autor: | Cosimo Antonio Prete, Gabriele Antonio De Vitis, Pierfrancesco Foglia |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
real-time performance
defect detection phase Computer science row level Image processing 02 engineering and technology production engineering computing pharmaceuticals Curvature production rate imperfect cylindrical shape Edge detection pharmaceutical market quality control automatic optical inspection pipes edge detection vibrations production batches row-level algorithm glass tube defect detection production phase pharmaceutical applications high-quality defect detection inspection systems image processing real-time inspection production process detection techniques processing time glass tube inspection perfect tube circular shape threshold algorithm defect size detection Moving average 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Throughput (business) 020206 networking & telecommunications Filter (signal processing) Vibration Signal Processing 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Algorithm Rotation (mathematics) Software |
| Popis: | In the case of the glass tube for pharmaceutical applications, high-quality defect detection is made via inspection systems based on image processing. Such processing must be fast enough to guarantee real-time inspection and to meet the increasing rate and quality required by the market. Defect detection is complex due to specific problems of the production process: vibration, rotation and irregularity of the tube. All these aspects prevent the efficient use of known techniques. The authors present an algorithm that decreases the processing time of the defect detection phase. The algorithm is based on a moving average filter working at row level, that allows to minimize the effects of rotation, vibration, and irregularity of the tube. Luminosity variations due to the tube curvature are cut by the filter and a threshold algorithm can be applied. They made the evaluation considering different solutions taken from literature. The algorithm outperforms, in processing time, all these solutions with increased accuracy. Experimental measures show that the algorithm achieves a throughput gain of 2.6 times with respect to Canny. They develop also a methodology to get the best values for the algorithm parameters directly at the factory, during the change of production batches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|