Uncertainty modelling using Dempster-Shafer theory for improving detection of weld defects

Abstract

This paper presents an approach that is based on the combined use of Dempster-Shafer (DS) theory and fuzzy sets for improving automatic detection of weld defects. It consists in modelling detection uncertainty in feature space through using the mass function weighted by membership degrees, and fusing the features of objects using DS combination rule. The method is demonstrated on the typical industrial application of weld inspection. The obtained results show that, by modelling detection uncertainty, a confidence level can be associated to each detected object, making the defect detection more precise and reliable.

DOI: 10.1016/S0167-8655(02)00276-3

Extracted Key Phrases

19 Figures and Tables

Cite this paper

@article{Kaftandjian2003UncertaintyMU, title={Uncertainty modelling using Dempster-Shafer theory for improving detection of weld defects}, author={Val{\'e}rie Kaftandjian and Olivier Dupuis and Daniel Babot and Yue Min Zhu}, journal={Pattern Recognition Letters}, year={2003}, volume={24}, pages={547-564} }