1 April 2016 A novel defect detection technique based on automatic detection of potential background
Author Affiliations +
Abstract
Automated defect detection from optical images is an efficient non-destructive evaluation technique for surface and structure health inspection. Background subtraction is a widely-used technique for automated defect detection. In background subtraction, an image of the part with no defect, called background image, is generated and subtracted from the defective part image; the resulted large differences are then considered as defects. In this paper, a new background generation technique is proposed that allows for efficient defect detection at a low-computational load. In this technique, a defect-free region is generated by approximately locating defects and removing them from the original image. The resulted defect-free region is now used to generate the background. The procedure and performance of the algorithm is illustrated by an example.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Masoumeh Aminzadeh, Masoumeh Aminzadeh, Thomas Kurfess, Thomas Kurfess, "A novel defect detection technique based on automatic detection of potential background", Proc. SPIE 9805, Health Monitoring of Structural and Biological Systems 2016, 98051Q (1 April 2016); doi: 10.1117/12.2223289; https://doi.org/10.1117/12.2223289
PROCEEDINGS
7 PAGES


SHARE
Back to Top