DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System

Gylfi Þór Guðmundsson; Christian Andreas Jacobsen; Hilmar Tryggvason; Björn Thór Jónsson

doi:10.1109/CBMI.2018.8516275

DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System

Gylfi Þór Guðmundsson, Christian Andreas Jacobsen, Hilmar Tryggvason, Björn Thór Jónsson

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

A vast number of algorithms and methods are proposed and developed every year in the domain of indexing and searching multimedia documents. Much of this work results in published papers and some sources are made openly available, but rarely will you find a fully working end-to-end system that has been pre-installed, configured, and is ready-to-go on a virtual machine available for download. In this paper we present such a system, the DeCP-Live web interface, that is built on top of the distributed, high-throughput, content-based image retrieval algorithm DeCP. The virtual machine is ready-to-go as on it we have pre-installed services, indexed openly available datasets, binaries for DeCP and DeCP-Live as well as the source code.

Original language	English
Title of host publication	Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI)
Number of pages	4
Place of Publication	La Rochelle, France
Publisher	IEEE
Publication date	Sept 2018
Pages	1-4
ISBN (Electronic)	978-1-5386-7021-7
DOIs	https://doi.org/10.1109/CBMI.2018.8516275
Publication status	Published - Sept 2018

Keywords

Content-based image retrieval
End-to-end system
Open source
Virtual machine

Access to Document

10.1109/CBMI.2018.8516275

cbmi2018.decpSubmitted manuscript, 4.25 MB

Cite this

@inproceedings{2f3c5d3a47a64fe8ad88b570d8b79fee,

title = "DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System",

abstract = "A vast number of algorithms and methods are proposed and developed every year in the domain of indexing and searching multimedia documents. Much of this work results in published papers and some sources are made openly available, but rarely will you find a fully working end-to-end system that has been pre-installed, configured, and is ready-to-go on a virtual machine available for download. In this paper we present such a system, the DeCP-Live web interface, that is built on top of the distributed, high-throughput, content-based image retrieval algorithm DeCP. The virtual machine is ready-to-go as on it we have pre-installed services, indexed openly available datasets, binaries for DeCP and DeCP-Live as well as the source code.",

keywords = "Content-based image retrieval, End-to-end system, Open source, Virtual machine",

author = "Gu{\dh}mundsson, {Gylfi {\TH}{\'o}r} and Jacobsen, {Christian Andreas} and Hilmar Tryggvason and J{\'o}nsson, {Bj{\"o}rn Th{\'o}r}",

year = "2018",

month = sep,

doi = "10.1109/CBMI.2018.8516275",

language = "English",

pages = "1--4",

booktitle = "Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI)",

publisher = "IEEE",

address = "United States",

}

DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System. / Guðmundsson, Gylfi Þór; Jacobsen, Christian Andreas; Tryggvason, Hilmar et al.
Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI). La Rochelle, France: IEEE, 2018. p. 1-4.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System

AU - Guðmundsson, Gylfi Þór

AU - Jacobsen, Christian Andreas

AU - Tryggvason, Hilmar

AU - Jónsson, Björn Thór

PY - 2018/9

Y1 - 2018/9

N2 - A vast number of algorithms and methods are proposed and developed every year in the domain of indexing and searching multimedia documents. Much of this work results in published papers and some sources are made openly available, but rarely will you find a fully working end-to-end system that has been pre-installed, configured, and is ready-to-go on a virtual machine available for download. In this paper we present such a system, the DeCP-Live web interface, that is built on top of the distributed, high-throughput, content-based image retrieval algorithm DeCP. The virtual machine is ready-to-go as on it we have pre-installed services, indexed openly available datasets, binaries for DeCP and DeCP-Live as well as the source code.

AB - A vast number of algorithms and methods are proposed and developed every year in the domain of indexing and searching multimedia documents. Much of this work results in published papers and some sources are made openly available, but rarely will you find a fully working end-to-end system that has been pre-installed, configured, and is ready-to-go on a virtual machine available for download. In this paper we present such a system, the DeCP-Live web interface, that is built on top of the distributed, high-throughput, content-based image retrieval algorithm DeCP. The virtual machine is ready-to-go as on it we have pre-installed services, indexed openly available datasets, binaries for DeCP and DeCP-Live as well as the source code.

KW - Content-based image retrieval

KW - End-to-end system

KW - Open source

KW - Virtual machine

U2 - 10.1109/CBMI.2018.8516275

DO - 10.1109/CBMI.2018.8516275

M3 - Article in proceedings

SP - 1

EP - 4

BT - Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI)

PB - IEEE

CY - La Rochelle, France

ER -

DeCP-Live: A Web-Interface for DeCP, a Distributed High-Throughput CBIR System

Abstract

Keywords

Access to Document

Fingerprint

Cite this