BUDÍKOVÁ, Petra, Michal BATKO and Pavel ZEZULA. Evaluation Platform for Content-based Image Retrieval Systems. In International Conference on Theory and Practice of Digital Libraries 2011, LNCS 6966. Berlin: Springer. p. 130-142, 12 pp. ISBN 978-3-642-24468-1. 2011.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Evaluation Platform for Content-based Image Retrieval Systems
Name in Czech Evaluační platforma pro obrazové vyhledávací systémy založené na obsahu
Authors BUDÍKOVÁ, Petra (203 Czech Republic, guarantor, belonging to the institution), Michal BATKO (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution).
Edition Berlin, International Conference on Theory and Practice of Digital Libraries 2011, LNCS 6966, p. 130-142, 12 pp. 2011.
Publisher Springer
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher Germany
Confidentiality degree is not subject to a state or trade secret
Publication form printed version "print"
RIV identification code RIV/00216224:14330/11:00049925
Organization unit Faculty of Informatics
ISBN 978-3-642-24468-1
UT WoS 000306258000015
Keywords in English large-scale image dataset; visual and textual annotation; ground truth; collaboration service
Tags DISA
Tags International impact, Reviewed
Changed by Changed by: RNDr. Michal Batko, Ph.D., učo 2907. Changed: 9/4/2014 12:52.
Abstract
In all subelds of information retrieval, test datasets and ground truth data are important tools for testing and comparison of new search methods. This is also reflected by the image retrieval community where several benchmarking activities have been created in past years using different test data. However, the number of available test collections is still rather small and the existing ones are often limited in size or accessible only to the participants of benchmarking competitions. In this work, we present a new freely-available large-scale dataset for evaluation of content-based image retrieval systems. The dataset consists of 20 million high-quality images with ve visual descriptors and rich and systematic textual annotations, a set of 100 test query objects and a semi-automatically collected ground truth data veried by users. Furthermore, we provide services that enable exploitation and collaborative expansion of the ground truth.
Links
GAP103/10/0886, research and development projectName: Vizuální vyhledávání obrázků na Webu (Acronym: VisualWeb)
Investor: Czech Science Foundation, Content-based Image Retrieval on the Web Scale
VF20102014004, research and development projectName: Multimediální analýza (Acronym: Multimediální analýza)
Investor: Ministry of the Interior of the CR
PrintDisplayed: 28/3/2024 10:53