Pregled bibliografske jedinice broj: 883828
Non-Parametric Context-Based Object Classification in Images
Non-Parametric Context-Based Object Classification in Images // Information Technology and Control, 46 (2017), 1; 86-99 doi:10.5755/j01.itc.46.1.13610 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 883828 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Non-Parametric Context-Based Object Classification
in Images
Autori
Rončević, Toma ; Braović, Maja ; Stipaničev, Darko
Izvornik
Information Technology and Control (1392-124X) 46
(2017), 1;
86-99
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
Object classification, image context, image segmentation, natural images
Sažetak
Segmentation and classification of objects in images is one of the most important and yet one of the most complex problems in computer vision. In this work we propose a new model for natural image object classification using contextual information at the level of image segments. Context modeling is largely independent of appearance-based classification and proposed model enables simple upgrade of existing systems with information from global and/or local context. Context modeling is based on non-parametric use of appearance-based classification results which is a novel approach compared to previous systems that model context on a limited number of rules expressed with a fixed set of parameters. Model implementation resulted in a system that, in our simulations, showed stable improvement of the appearance-based object classification.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split,
Sveučilište u Splitu Sveučilišni odjel za stručne studije
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus
