Pregled bibliografske jedinice broj: 526327
Context-Based Natural Image Parsing: A Critical Survey
Context-Based Natural Image Parsing: A Critical Survey // SoftCOM 2011 - 19. International Conference on Software, Telecommunications and Computer Networks / Rožić, Nikola ; Begušić, Dinko (ur.).
Split: Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 2011. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 526327 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Context-Based Natural Image Parsing: A Critical Survey
Autori
Rončević, Toma ; Braović, Maja ; Stipaničev, Darko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
SoftCOM 2011 - 19. International Conference on Software, Telecommunications and Computer Networks
/ Rožić, Nikola ; Begušić, Dinko - Split : Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 2011
ISBN
978-953-290-027-9
Skup
SoftCOM 2011 - 19. International Conference on Software, Telecommunications and Computer Networks
Mjesto i datum
Dubrovnik, Hrvatska; Hvar, Hrvatska; Split, Hrvatska, 15.09.2011. - 17.09.2011
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
context-based image parsing; semantics
Sažetak
Image parsing is an essential part of a large number of image understanding systems. It encompasses techniques for segmenting images into meaningful objects and labeling them with semantic classes. Both sub-problems of segmentation and classification are impossible to deal with in most natural domains without implicit or explicit consideration of context provided by other sources (i.e. sensors or a domain knowledge) or emerging from the image itself (neighborhood or global image features). In this paper we will discuss different approaches that exploit the image context in order to achieve reliable parsing of natural scenes.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
023-0232005-2003 - AgISEco - Agentski orijentirani inteligentni sustavi nadzora i zaštite okoliša (Stipaničev, Darko, MZOS ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split