Pregled bibliografske jedinice broj: 768435
Automatic image annotation refinement using fuzzy inference algorithms
Automatic image annotation refinement using fuzzy inference algorithms // Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology / Luis Magdalena Layos (ur.).
Gijon: Atlantis Press, 2015. str. 1446-1451 doi:10.2991/ifsa-eusflat-15.2015.205 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 768435 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Automatic image annotation refinement using fuzzy
inference algorithms
Autori
Ivašić-Kos, Marina ; Pobar, Miran ; Ribarić, Slobodan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology
/ Luis Magdalena Layos - Gijon : Atlantis Press, 2015, 1446-1451
Skup
16th World Congress of the International Fuzzy Systems Association (IFSA) and the 9th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT)
Mjesto i datum
Gijón, Španjolska, 30.06.2015. - 03.07.2015
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
automatic image annotation ; annotation refinement ; fuzzy knowledge representation scheme ; fuzzy inference algorithms
Sažetak
Facilitating tasks such as image search is one of the goals of image annotation methods that automatically assign keywords to images. In order to achieve as accu-rate annotation on object level as possible, and to reduce negative influence of misclassified objects on the inference of scenes, a knowledge based refinement of object classification results is proposed. A fuzzy knowledge representation scheme called KRFPNr is used to represent knowledge about objects and their relations. Fuzzy inheritance and intersection algorithms are used to refine the image annotation on object level by discarding or replacing object labels that do not fit the context.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
MZO-ZP-036-0361935-1954 - Teorija, modeliranje i uporaba autonomno orijentiranih računarskih struktura (Ribarić, Slobodan, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Fakultet informatike i digitalnih tehnologija, Rijeka
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Conference Proceedings Citation Index - Science (CPCI-S)
