Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
536705 | Pattern Recognition Letters | 2007 | 12 Pages |
Abstract
This paper proposes a novel method based on Dempster–Shafer (belief function) theory for the detection of blotches in digitized archive film sequences. The detection scheme relies on the fusion of two uncorrelated blotch detectors, one working in the spatial domain and the other one in the temporal domain. The imprecision and uncertainty of both detectors have been modeled using belief function theory, and their combination improves the decision, by taking into account the ignorance and the conflict between detectors. Quantitative evaluation using real blotches ground truth shows that this combination scheme improves the global performance, and compares favorably with two classical blotch detectors.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Sorin Tilie, Isabelle Bloch, Louis Laborelli,