Feature selection for surface defect classification of extruded aluminum profiles
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7110256
- Type
- D - Journal article
- DOI
-
10.1007/s00170-015-7514-3
- Title of journal
- International Journal of Advanced Manufacturing Technology
- Article number
- -
- First page
- 33
- Volume
- 83
- Issue
- 1
- ISSN
- 0268-3768
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
2
- Research group(s)
-
B - Computational Intelligence
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A novel method utilising machine vision and machine learning for surface defect detection, identification and classification with superior performance (when compared with other best techniques). Although implemented on aluminium profiles, the approach is easily extendable to other surfaces, and has influenced works on defects detection and inspection in metallic surfaces as well as specific applications, such as railway tracks inspection [Ye et al, IET Image Processing 14(12)] or welding quality [Chu, International Journal of Precision Engineering and Manufacturing 18(6)].
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -