Open AccessProceedings Article
Image processing for automatic defect detection in industrial radiographic images
A. Kehoe,G.A. Parker,A. LeBlanc +2 more
- 18 Jul 1989
- pp 202-206
4
TL;DR: In this paper, two new image processing techniques for the automatic detection of defects in industrial radiographic images are described, which is part of a project concerned with the development of an automatic radiographic inspection system to provide on-line quality assurance for engineering components.
read more
Abstract: Due to the nature of image formation and the resultant image quality the radiographic image is very difficult to interpret which makes the detection of defects inconsistent. In order to improve this situation image processing techniques are applied to the inspection process. This paper describes two new image processing techniques for the automatic detection of defects in industrial radiographic images. This work is part of a project concerned with the development of an automatic radiographic inspection system to provide on-line quality assurance for engineering components.<
>
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Automatic classification of weld defects using simulated data and an MLP neural network
TL;DR: In this article, a multi-layer perceptron (MLP) neural network was trained using shape parameters extracted from the simulated images of weld defects, and the optimised set of nine shape descriptors gave the highest classification accuracy of 100%.
•Dissertation
An investigation into sub-surface strain measurement using X-ray radioscopy
Richard John Drew
- 01 Jan 1999
TL;DR: The research covered by this thesis tested radioscopic images and showed them to be suitable for strain measurement, and an automatic method of identifying, and correcting for the distortion was implemented.
6
An automated system for the radiographic inspection of castings
A Kehoe,G A Parker +1 more
TL;DR: In this article, the authors describe a novel approach to the design of an automated system for conventional radiographic inspection of cast engineering components, which incorporates a series of conventional image processing techniques to efficiently detect and analyse defects in the radiographic image.