Paper Info
Title
Iterative Refinement of Possibility Distributions by Learning for Pixel-Based Classification.
Abstract
This paper proposes an approach referred as: iterative refinement of possibility distributions by learning (IRPDL) for pixel-based image classification. The IRPDL approach is based on the use of possibilistic reasoning concepts exploiting expert knowledge sources as well as ground possibilistic seeds learning. The set of seeds is constructed by incrementally updating and refining the possibility distributions. Synthetic images as well as real images from the RIDER Breast MRI database are being used to evaluate the IRPDL performance. Its performance is compared with three relevant reference methods: region growing, semi-supervised fuzzy pattern matching, and Markov random fields. The IRDPL performance (in terms of recognition rate, 87.3%) is close to the Markovian method (88.8%) that is considered to be the reference in pixel-based image classification. IRPDL outperforms the other two methods, respectively, at the recognition rates of 83.9% and 84.7%. In addition, the proposed IRPDL requires fewer parameters for the mathematical representation and presents a reduced computational complexity.
Year
DOI
Venue
2016
10.1109/TIP.2016.2574992
IEEE Trans. Image Processing
Keywords
Field
DocType
Possibility theory,Image classification,Uncertainty,Context,Histograms,Pattern matching,Image segmentation
Iterative refinement,Computer vision,Pattern recognition,Image segmentation,Possibility theory,Artificial intelligence,Region growing,Pixel,Real image,Contextual image classification,Pattern matching,Mathematics
Journal
Volume
Issue
ISSN
25
8
1057-7149
Citations 
PageRank 
References 
4
0.45
21
Authors
5
Name
Order
Citations
PageRank
Bassem Alsahwa192.62
Basel Solaiman212735.05
Shaban Almouahed3216.73
Éloi Bossé438626.19
Didier Gueriot5306.20