D 2011

Searching for Sub-images using Sequence Alignment

HOMOLA, Tomáš, Vlastislav DOHNAL and Pavel ZEZULA

Basic information

Original name

Searching for Sub-images using Sequence Alignment

Authors

HOMOLA, Tomáš (203 Czech Republic, belonging to the institution), Vlastislav DOHNAL (203 Czech Republic, guarantor, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

Los Alamitos, California, IEEE International Symposium on Multimedia (ISM 2011), p. 1-8, 8 pp. 2011

Publisher

IEEE Computer Society

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

RIV identification code

RIV/00216224:14330/11:00049949

Organization unit

Faculty of Informatics

ISBN

978-1-4577-2015-4

DOI

Keywords in English

image matching; sub-image retrieval; local image features; sequence alignment

Tags

Tags

International impact, Reviewed
Změněno: 28/2/2012 08:40, doc. RNDr. Vlastislav Dohnal, Ph.D.

Abstract

V originále

The availability of various photo archives and photo sharing systems made similarity searching much more important because the photos are not usually conveniently tagged. So the photos (images) need to be searched by their content. Moreover, it is important not only to compare images with a query holistically but also to locate images that contain the query as their part. The query can be a picture of a person, building, or an abstract object and the task is to retrieve images of the query object but from a different perspective or images capturing a global scene containing the query object. This retrieval is called the sub-image searching. In this paper, we propose an algorithm for retrieving database images by their similarity to and containment of a query. The novelty of it lies in application of a sequence alignment algorithm, which is commonly used in text retrieval. This forms an orthogonal solution to currently used approaches based on inverted files. The proposed algorithm is evaluated on a real-life data set containing photographs where images of logos are searched. It was compared to a state-of-the-art method and the improvement of 20\% in average mean precision was obtained.

Links

GAP103/10/0886, research and development project
Name: Vizuální vyhledávání obrázků na Webu (Acronym: VisualWeb)
Investor: Czech Science Foundation, Content-based Image Retrieval on the Web Scale
GA201/09/0683, research and development project
Name: Vyhledávání v rozsáhlých multimediálních databázích
Investor: Czech Science Foundation, Similarity Searching in Very Large Multimedia Databases
MUNI/A/0922/2009, interní kód MU
Name: Aplikovaný výzkum Fakulty informatiky (Acronym: AVFI)
Investor: Masaryk University, Category A
VF20102014004, research and development project
Name: Multimediální analýza (Acronym: Multimediální analýza)
Investor: Ministry of the Interior of the CR

Files attached

ism2011-camera-ready.pdf
Request the author's version of the file