Human-Centered Content-Based Image Retrieval

Egon van den Broek; Thijs Kok; Theo E. Schouten; Louis G. Vuurpijl

doi:10.1117/12.767190

Human-Centered Content-Based Image Retrieval

Egon van den Broek, Thijs Kok, Theo E. Schouten, Louis G. Vuurpijl

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

38 Downloads (Pure)

Abstract

A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR.

Original language	Undefined
Title of host publication	Human Vision and Electronic Imaging XIII
Editors	Bernice E. Rogowitz, Thrasyvoulos N. Pappas
Place of Publication	Bellingham, WA, USA
Publisher	SPIE - The International Society for Optical Engineering
Pages	68061L
Number of pages	12
ISBN (Print)	978-0-81946-978-6
DOIs	https://doi.org/10.1117/12.767190
Publication status	Published - 28 Jan 2008
Event	Human Vision and Electronic Imaging XIII - San Jose, CA, USA Duration: 27 Jan 2008 → 31 Jan 2008

Publication series

Name	Proceedings of SPIE
Publisher	SPIE - The International Society for Optical Engineering
Volume	6806
ISSN (Print)	0277-786X

Conference

Conference	Human Vision and Electronic Imaging XIII
Period	27/01/08 → 31/01/08
Other	27-31 January 2008

Keywords

METIS-252707
Multimedia for Art ReTrieval (M4ART)
Benchmarking
Content-Based Image Retrieval
IR-58738
user-system interaction
human color perception
color categories
Texture
experts
M4ART
HMI-MR: MULTIMEDIA RETRIEVAL
EWI-21108
laypersons

Access to Document

10.1117/12.767190

VandenBroek08-Human-centered_content-based_image_retrieval

Cite this

@inproceedings{4803de5aade14f1d83ccd17dabe42c78,

title = "Human-Centered Content-Based Image Retrieval",

abstract = "A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR.",

keywords = "METIS-252707, Multimedia for Art ReTrieval (M4ART), Benchmarking, Content-Based Image Retrieval, IR-58738, user-system interaction, human color perception, color categories, Texture, experts, M4ART, HMI-MR: MULTIMEDIA RETRIEVAL, EWI-21108, laypersons",

author = "{van den Broek}, Egon and Thijs Kok and Schouten, {Theo E.} and Vuurpijl, {Louis G.}",

year = "2008",

month = jan,

day = "28",

doi = "10.1117/12.767190",

language = "Undefined",

isbn = "978-0-81946-978-6",

series = "Proceedings of SPIE",

publisher = "SPIE - The International Society for Optical Engineering",

pages = "68061L",

editor = "Rogowitz, {Bernice E.} and Pappas, {Thrasyvoulos N.}",

booktitle = "Human Vision and Electronic Imaging XIII",

note = "null ; Conference date: 27-01-2008 Through 31-01-2008",

}

van den Broek, E, Kok, T, Schouten, TE & Vuurpijl, LG 2008, Human-Centered Content-Based Image Retrieval. in BE Rogowitz & TN Pappas (eds), Human Vision and Electronic Imaging XIII. Proceedings of SPIE, vol. 6806, SPIE - The International Society for Optical Engineering, Bellingham, WA, USA, pp. 68061L, Human Vision and Electronic Imaging XIII, 27/01/08. https://doi.org/10.1117/12.767190

Human-Centered Content-Based Image Retrieval. / van den Broek, Egon; Kok, Thijs; Schouten, Theo E.; Vuurpijl, Louis G.

Human Vision and Electronic Imaging XIII. ed. / Bernice E. Rogowitz; Thrasyvoulos N. Pappas. Bellingham, WA, USA : SPIE - The International Society for Optical Engineering, 2008. p. 68061L (Proceedings of SPIE; Vol. 6806).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Human-Centered Content-Based Image Retrieval

AU - van den Broek, Egon

AU - Kok, Thijs

AU - Schouten, Theo E.

AU - Vuurpijl, Louis G.

PY - 2008/1/28

Y1 - 2008/1/28

N2 - A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR.

AB - A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR.

KW - METIS-252707

KW - Multimedia for Art ReTrieval (M4ART)

KW - Benchmarking

KW - Content-Based Image Retrieval

KW - IR-58738

KW - user-system interaction

KW - human color perception

KW - color categories

KW - Texture

KW - experts

KW - M4ART

KW - HMI-MR: MULTIMEDIA RETRIEVAL

KW - EWI-21108

KW - laypersons

U2 - 10.1117/12.767190

DO - 10.1117/12.767190

M3 - Conference contribution

SN - 978-0-81946-978-6

T3 - Proceedings of SPIE

SP - 68061L

BT - Human Vision and Electronic Imaging XIII

A2 - Rogowitz, Bernice E.

A2 - Pappas, Thrasyvoulos N.

PB - SPIE - The International Society for Optical Engineering

CY - Bellingham, WA, USA

Y2 - 27 January 2008 through 31 January 2008

ER -