Paper
25 October 2016 Scratch detection in metal surface by blasting using Gabor filters
Shuangchun Liu, Hongwei Jing
Author Affiliations +
Proceedings Volume 9686, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices; 96860W (2016) https://doi.org/10.1117/12.2243220
Event: Eighth International Symposium on Advanced Optical Manufacturing and Testing Technology (AOMATT2016), 2016, Suzhou, China
Abstract
Sand blasting process can produce fine random concave and convex surfaces on the surface of the workpiece, which make the collected image background of the workpiece complex and the defects difficult to detect. Especially for the detection of low-contrast scratches, scratch depth is less than the depth of sand blasting surface. Common edge detection methods and threshold segmentation methods are difficult to effectively extract the scratch defect. According to the vertical characteristics of scratches direction in the spatial domain and the spatial-frequency domain, a method based on Gabor filter is proposed for the detection of scratch defect. Firstly, 36 Gabor filters with different directions are used to extract the directional feature of the image. Then, using the gray threshold method to segment the scratch regions in 36 different directions and merge the scratch regions. Finally, the morphological processing is used to remove the noise interference and connect the scratch regions which are not continuous. The experimental results show that the method is feasible and robust. Compared with the hysteresis threshold algorithm, the algorithm extracts the edge of the scratch without burr and has high precision.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shuangchun Liu and Hongwei Jing "Scratch detection in metal surface by blasting using Gabor filters", Proc. SPIE 9686, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices, 96860W (25 October 2016); https://doi.org/10.1117/12.2243220
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Defect detection

Metals

Image processing

Image filtering

Image segmentation

Detection and tracking algorithms

Edge detection

Back to Top