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.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2016.2574992DOI Listing

Publication Analysis

Top Keywords

possibility distributions
12
iterative refinement
8
refinement possibility
8
distributions learning
8
pixel-based image
8
image classification
8
classification irpdl
8
irpdl
5
learning pixel-based
4
pixel-based classification
4

Similar Publications

Pleurotus ostreatus is a nutrient-dense edible fungus renowned for its delicate texture, appealing flavor, and numerous potential health benefits. Simultaneous extraction within the framework of food resource processing facilitates the concurrent isolation and analysis of multiple target compounds. In this study, an ethanol/salt aqueous two-phase system (ATPS) was employed to extract polysaccharides (PS) and proteins from P.

View Article and Find Full Text PDF

Management of patients with urinary incontinence in senior age.

Cent Eur J Public Health

December 2024

Department of Public Health and Hygiene, Faculty of Medicine, Pavol Jozef Safarik University in Kosice, Kosice, Slovak Republic.

Objectives: Urinary incontinence is an extremely stressful and often debilitating disease, increasing morbidity in society. The aim of the work is to point out the problems of the management of incontinent patients - seniors in the context of their quality of life as well as treatment costs to find ways to make the widest possible public awareness of the fact that in most cases incontinence is solvable in terms of improving the quality of life.

Methods: The group consisted of 100 patients with urinary incontinence who were treated with conservative medical procedures at the urological outpatient clinic of the Railway Hospital in Košice.

View Article and Find Full Text PDF

Purpose: The dentato-rubro-thalamo-cortical tract (DRTC) is considered to play a crucial role across tremor disorders including tremor dominant Parkinson's disease (TDPD) and essential tremor plus (ETP). This study aims to comprehensively evaluate microstructural integrity of the DRTC using single-compartment, i.e.

View Article and Find Full Text PDF

There are few taxonomic studies of the harpacticoid family Idyanthidae Lang, 1944 in the Pacific Ocean. As a first report of the family in this region, one species of the monotypic genus Lang, 1948 and two species of the genus Sars, 1905 are described from sublittoral habitats around the Korean Peninsula. sp.

View Article and Find Full Text PDF

The consequences of climate change, accelerated by anthropogenic activities, have different effects on different ecosystems, and the severity of these effects is predicted to increase in the near future. The number of studies investigating how forest ecosystems respond to these changes is increasing. However, there remains a significant gap in research concerning how saproxylic organisms-one of the key contributors to the healthy functioning of these fragile ecosystems-will respond to the consequences of climate change.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!