MUFIN at ImageCLEF 2011: Success or Failure?

D 2011

MUFIN at ImageCLEF 2011: Success or Failure?

BUDÍKOVÁ, Petra, Michal BATKO a Pavel ZEZULA

Základní údaje

Originální název

MUFIN at ImageCLEF 2011: Success or Failure?

Název česky

MUFIN na soutěži ImageCLEF 2011: Úspěch nebo selhání?

Autoři

BUDÍKOVÁ, Petra (203 Česká republika, garant, domácí), Michal BATKO (203 Česká republika, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

Amsterdam, CLEF 2011 Labs and Workshop, Notebook Papers; CEUR Workshop Proceedings Vol. 1177, od s. 1-12, 12 s. 2011

Nakladatel

CLEF

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Kód RIV

RIV/00216224:14330/11:00050011

Organizační jednotka

Fakulta informatiky

ISSN

Klíčová slova anglicky

image annotation; content-based image retrieval; ImageCLEF Photo Annotation Task;

Štítky

DISA

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 5. 5. 2016 16:02, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

In all fields of research it is important to discuss and compare various methods that are being proposed to solve given problems. In image retrieval, the ImageCLEF competitions provide such comparison platform. We have participated in the Photo Annotation Task of the ImageCLEF 2011 competition with a system based on the MUFIN Annotation Tool. Our approach is, in contrast to typical classifier solutions, based on a general annotation system for web images that provides general keywords for arbitrary image. However, the free-text annotation needs to be transformed into the 99 concepts given by the competition task. The transformation process is described in detail in the first part of this paper. In the second part, we discuss the results achieved by our solution. Even though the free-text annotation approach was not as successful as the classifier-based approaches, the results are competitive especially for the concepts involving real-world objects. On the other hand, our approach does not require training and is scalable to any number of concepts.

Návaznosti

GAP103/10/0886, projekt VaV

Název: Vizuální vyhledávání obrázků na Webu (Akronym: VisualWeb)

Investor: Grantová agentura ČR, Vizuální vyhledávání obrázků na Webu

VF20102014004, projekt VaV

Název: Multimediální analýza (Akronym: Multimediální analýza)

Investor: Ministerstvo vnitra ČR, Multimediální analýza

Citovat

BUDÍKOVÁ, Petra, Michal BATKO a Pavel ZEZULA. MUFIN at ImageCLEF 2011: Success or Failure?. Online. In CLEF 2011 Labs and Workshop, Notebook Papers; CEUR Workshop Proceedings Vol. 1177. Amsterdam: CLEF, 2011, s. 1-12. ISSN 1613-0073.

@inproceedings{951142,
   author = {Budíková, Petra and Batko, Michal and Zezula, Pavel},
   address = {Amsterdam},
   booktitle = {CLEF 2011 Labs and Workshop, Notebook Papers; CEUR Workshop Proceedings Vol. 1177},
   keywords = {image annotation; content-based image retrieval; ImageCLEF Photo Annotation Task;},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Amsterdam},
   pages = {1-12},
   publisher = {CLEF},
   title = {MUFIN at ImageCLEF 2011: Success or Failure?},
   url = {http://ceur-ws.org/Vol-1177/},
   year = {2011}
}

TY  - JOUR
ID  - 951142
AU  - Budíková, Petra - Batko, Michal - Zezula, Pavel
PY  - 2011
TI  - MUFIN at ImageCLEF 2011: Success or Failure?
PB  - CLEF
CY  - Amsterdam
KW  - image annotation
KW  - content-based image retrieval
KW  - ImageCLEF Photo Annotation Task;
UR  - http://ceur-ws.org/Vol-1177/
L2  - http://ceur-ws.org/Vol-1177/
N2  - In all fields of research it is important to discuss and compare various methods that are being proposed to solve given problems. In image retrieval, the ImageCLEF competitions provide such comparison platform. We have participated in the Photo Annotation Task of the ImageCLEF 2011 competition with a system based on the MUFIN Annotation Tool. Our approach is, in contrast to typical classifier solutions, based on a general annotation system for web images that provides general keywords for arbitrary image. However, the free-text annotation needs to be transformed into the 99 concepts given by the competition task. The transformation process is described in detail in the first part of this paper. In the second part, we discuss the results achieved by our solution. Even though the free-text annotation approach was not as successful as the classifier-based approaches, the results are competitive especially for the concepts involving real-world objects. On the other hand, our approach does not require training and is scalable to any number of concepts.
ER  -

BUDÍKOVÁ, Petra, Michal BATKO a Pavel ZEZULA. MUFIN at ImageCLEF 2011: Success or Failure?. Online. In \textit{CLEF 2011 Labs and Workshop, Notebook Papers; CEUR Workshop Proceedings Vol. 1177}. Amsterdam: CLEF, 2011, s.~1-12. ISSN~1613-0073.

Podrobný výpis o publikaci