Study on crack features in images of fluorescent magnetic particle inspection for railway wheelsets
Crack features in the images of fluorescent magnetic particle inspection (FMPI) for railway wheelsets are studied in this paper. Firstly, according to the curvilinear structure of the cracks, a ridge-line detection (RLD) approach is used to extract ridge lines of the image structures as suspected cracks. Secondly, the shapes of the ridge lines and their image structures are exploited, which leads to shape features being extracted from the ridge lines and an additional restriction in ridge-line detection. Thirdly, the local textures of the suspected cracks are analysed and a texture feature is proposed based on averaging the modified scale-invariant feature transform (SIFT) descriptors of the points on the suspected crack. Experiments on real FMPI images of railway wheelsets prove the effectiveness of the proposed features. Among the tested algorithms, the proposed algorithm, which uses the modified ridge-line detection approach to extract suspected cracks and the texture feature to distinguish real cracks from all suspected cracks, achieves the highest recall and precision, both of which are over 90%.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: September 1, 2018
More about this publication?
- Official Journal of The British Institute of Non-Destructive Testing - includes original research and devlopment papers, technical and scientific reviews and case studies in the fields of NDT and CM.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Information for Advertisers
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites