LOKOČ, Jakub, David NOVÁK, Michal BATKO and Tomáš SKOPAL. Visual Image Search: Feature Signatures or/and Global Descriptors. In Navarro, Gonzalo and Pestov, Vladimir. Similarity Search and Applications. Berlin / Heidelberg: Springer, 2012. p. 177-191. ISBN 978-3-642-32152-8. doi:10.1007/978-3-642-32153-5_13.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Visual Image Search: Feature Signatures or/and Global Descriptors
Authors LOKOČ, Jakub (203 Czech Republic), David NOVÁK (203 Czech Republic, guarantor, belonging to the institution), Michal BATKO (203 Czech Republic, belonging to the institution) and Tomáš SKOPAL (203 Czech Republic).
Edition Berlin / Heidelberg, Similarity Search and Applications, p. 177-191, 15 pp. 2012.
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"
WWW publisher site
Impact factor Impact factor: 0.402 in 2005
RIV identification code RIV/00216224:14330/12:00057558
Organization unit Faculty of Informatics
ISBN 978-3-642-32152-8
ISSN 0302-9743
Doi http://dx.doi.org/10.1007/978-3-642-32153-5_13
Keywords in English similarity search; CBIR; global visual descriptors; visual signatures; SQFD
Tags International impact, Reviewed
Changed by Changed by: RNDr. Pavel Šmerk, Ph.D., učo 3880. Changed: 23. 4. 2013 13:17.
The success of content-based retrieval systems stands or falls with the quality of the utilized similarity model. In the case of having no additional keywords or annotations provided with the multimedia data, the hard task is to guarantee the highest possible retrieval precision using only content-based retrieval techniques. In this paper we push the visual image search a step further by testing effective combination of two orthogonal approaches – the MPEG-7 global visual descriptors and the feature signatures equipped by the Signature Quadratic Form Distance. We investigate various ways of descriptor combinations and evaluate the overall effectiveness of the search on three different image collections. Moreover, we introduce a new image collection, TWIC, designed as a larger realistic image collection providing ground truth. In all the experiments, the combination of descriptors proved its superior performance on all tested collections. Furthermore, we propose a re-ranking variant guaranteeing efficient yet effective image retrieval.
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
GPP202/10/P220, research and development projectName: Podobnostní vyhledávání s konstantní škálovatelností (Acronym: SIM-SCALE)
Investor: Czech Science Foundation
Type Name Uploaded/Created by Uploaded/Created Rights
2012_-_Visual_Image_Search_Feature_Signatures_orand_Global_Descriptors.pdf   File version Novák, D. 5. 9. 2012


Address within IS
Address for the users outside IS
Address within Manager
Address within Manager for the users outside IS
Wed 5. 9. 2012 14:13


Right to read
  • anyone on the Internet
Right to upload
Right to administer:
  • a concrete person prof. RNDr. Tomáš Skopal, Ph.D., učo 101659
  • a concrete person doc. RNDr. Jakub Lokoč, Ph.D., učo 117689
  • a concrete person RNDr. Michal Batko, Ph.D., učo 2907
  • a concrete person RNDr. Pavel Šmerk, Ph.D., učo 3880
  • a concrete person RNDr. David Novák, Ph.D., učo 4335


Open the file
Download file.
Address within IS
Address for the users outside IS
File type
PDF (application/pdf)
1 MB
Hash md5
Wed 5. 9. 2012 14:13


Open the file
Download file.
Address within IS
Address for the users outside IS
File type
plain text (text/plain)
38,9 KB
Hash md5
Wed 5. 9. 2012 14:15
Report a file uploaded without authorization. Displayed: 1. 7. 2022 05:37