Image region entropy: A measure of "visualness" of web images associated with one concept

Keiji Yanai; Kobus Barnard

doi:10.1145/1101149.1101241

Image region entropy: A measure of "visualness" of web images associated with one concept

Keiji Yanai, Kobus Barnard

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

64 Scopus citations

Abstract

We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

Original language	English (US)
Title of host publication	Proceedings of the 13th ACM International Conference on Multimedia, MM 2005
Pages	419-422
Number of pages	4
DOIs	https://doi.org/10.1145/1101149.1101241
State	Published - 2005
Event	13th ACM International Conference on Multimedia, MM 2005 - Singapore, Singapore Duration: Nov 6 2005 → Nov 11 2005

Publication series

Name	Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

Other

Other	13th ACM International Conference on Multimedia, MM 2005
Country/Territory	Singapore
City	Singapore
Period	11/6/05 → 11/11/05

Keywords

Image annotation
Probabilistic image selection
Web image mining

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Human-Computer Interaction
Software

Access to Document

10.1145/1101149.1101241

Cite this

Image region entropy: A measure of "visualness" of web images associated with one concept. / Yanai, Keiji; Barnard, Kobus.
Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. 2005. p. 419-422 (Proceedings of the 13th ACM International Conference on Multimedia, MM 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yanai, K & Barnard, K 2005, Image region entropy: A measure of "visualness" of web images associated with one concept. in Proceedings of the 13th ACM International Conference on Multimedia, MM 2005. Proceedings of the 13th ACM International Conference on Multimedia, MM 2005, pp. 419-422, 13th ACM International Conference on Multimedia, MM 2005, Singapore, Singapore, 11/6/05. https://doi.org/10.1145/1101149.1101241

@inproceedings{156dc16797254ea4918cb53569d09055,

title = "Image region entropy: A measure of {"}visualness{"} of web images associated with one concept",

abstract = "We propose a new method to measure {"}visualness{"} of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept {"}X{"} or {"}non-X{"}, and computes an entropy measure which represents {"}visualness{"} of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.",

keywords = "Image annotation, Probabilistic image selection, Web image mining",

author = "Keiji Yanai and Kobus Barnard",

year = "2005",

doi = "10.1145/1101149.1101241",

language = "English (US)",

isbn = "1595930442",

series = "Proceedings of the 13th ACM International Conference on Multimedia, MM 2005",

pages = "419--422",

booktitle = "Proceedings of the 13th ACM International Conference on Multimedia, MM 2005",

note = "13th ACM International Conference on Multimedia, MM 2005 ; Conference date: 06-11-2005 Through 11-11-2005",

}

TY - GEN

T1 - Image region entropy

T2 - 13th ACM International Conference on Multimedia, MM 2005

AU - Yanai, Keiji

AU - Barnard, Kobus

PY - 2005

Y1 - 2005

N2 - We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

AB - We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

KW - Image annotation

KW - Probabilistic image selection

KW - Web image mining

UR - http://www.scopus.com/inward/record.url?scp=36849034452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36849034452&partnerID=8YFLogxK

U2 - 10.1145/1101149.1101241

DO - 10.1145/1101149.1101241

M3 - Conference contribution

AN - SCOPUS:36849034452

SN - 1595930442

SN - 9781595930446

T3 - Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

SP - 419

EP - 422

BT - Proceedings of the 13th ACM International Conference on Multimedia, MM 2005

Y2 - 6 November 2005 through 11 November 2005

ER -

Image region entropy: A measure of "visualness" of web images associated with one concept

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this