About: Building a Web-scale Image Similarity Search System

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Building a Web-scale Image Similarity Search System Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
Description	As the number of digital images is growing fast and Content-based Image Retrieval (CBIR) is gaining in popularity, CBIR systems should leap towards Web-scale datasets. In this paper, we report on our experience in building an experimental similarity search system on a test collection of more than 50 million images. The first big challenge we have been facing was obtaining a collection of images of this scale with the corresponding descriptive features. We have tackled the non-trivial process of image crawling and extraction of several MPEG-7 descriptors. The result of this effort is a test collection, the first of such scale, opened to the research community for experiments and comparisons. The second challenge was to develop indexing and searching mechanisms able to scale to the target size and to answer similarity queries in real-time. We have achieved this goal by creating sophisticated centralized and distributed structures based purely on the metric space model of data. As the number of digital images is growing fast and Content-based Image Retrieval (CBIR) is gaining in popularity, CBIR systems should leap towards Web-scale datasets. In this paper, we report on our experience in building an experimental similarity search system on a test collection of more than 50 million images. The first big challenge we have been facing was obtaining a collection of images of this scale with the corresponding descriptive features. We have tackled the non-trivial process of image crawling and extraction of several MPEG-7 descriptors. The result of this effort is a test collection, the first of such scale, opened to the research community for experiments and comparisons. The second challenge was to develop indexing and searching mechanisms able to scale to the target size and to answer similarity queries in real-time. We have achieved this goal by creating sophisticated centralized and distributed structures based purely on the metric space model of data. (en)
Title	Building a Web-scale Image Similarity Search System Building a Web-scale Image Similarity Search System (en)
skos:prefLabel	Building a Web-scale Image Similarity Search System Building a Web-scale Image Similarity Search System (en)
skos:notation	RIV/00216224:14330/10:00042682!RIV11-GA0-14330___
http://linked.open...avai/riv/aktivita	P S
http://linked.open...avai/riv/aktivity	P(1M0545), P(GA201/09/0683), P(GD102/09/H042), P(GP201/08/P507), S
http://linked.open...iv/cisloPeriodika	3
http://linked.open...vai/riv/dodaniDat	2011
http://linked.open...aciTvurceVysledku	Sedmidubský, Jan Zezula, Pavel Novák, David Batko, Michal
http://linked.open.../riv/druhVysledku	J - Článek v odborném periodiku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Masarykova univerzita / Fakulta informatiky
http://linked.open...dnocenehoVysledku	249361
http://linked.open...ai/riv/idVysledku	RIV/00216224:14330/10:00042682
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	similarity search; content-based image retrieval; metric space; MPEG-7 descriptors; peer-to-peer search network (en)
http://linked.open.../riv/klicoveSlovo	similarity search metric space content-based image retrieval MPEG-7 descriptors peer-to-peer search network
http://linked.open...odStatuVydavatele	US - Spojené státy americké
http://linked.open...ontrolniKodProRIV	[4CB6BADB7436]
http://linked.open...i/riv/nazevZdroje	Multimedia Tools and Applications
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	4 (xsd:int)
http://linked.open...cetTvurcuVysledku	8 (xsd:int)
http://linked.open...vavai/riv/projekt	Similarity searching in very large multimedia databases Institute for Theoretical Computer Science Mathematical and Engineering Approaches to Developing Reliable and Secure Concurrent and Distributed Computer Systems Complex similarity searching in very large data collections
http://linked.open...UplatneniVysledku	2010
http://linked.open...v/svazekPeriodika	47
http://linked.open...iv/tvurceVysledku	Novák, David Sedmidubský, Jan Batko, Michal Zezula, Pavel Falchi, Fabrizio Lucchese, Claudio Perego, Raffaele Rabitti, Fausto
issn	1380-7501
number of pages	31 (xsd:int)
http://localhost/t...ganizacniJednotka	14330

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software