Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval

Chi Ren Shyu, Adrian Sorin Barb, Curt H. Davis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Query methods using visual semantics play an important role in horizontal interoperability of geospatial databases. However, a common practice is to manually label visual semantics of images using text annotations. This approach is subjective and, more importantly, impractical when dealing with large-scale geospatial image databases. In this paper, we propose a knowledge discovery (KDD) framework to link low-level image features with high-level visual semantics in an attempt to automate the process of retrieving semantically similar images. Our framework first extracts association rules that correlate semantic terms with discrete intervals of individual features. It then applies possibility functions to mathematically model visual semantics. Our approach provides a unique way to query image databases using semantics, and to potentially make available a knowledge exchange method for the geospatial community.

Original languageEnglish (US)
Title of host publication25th Anniversary IGARSS 2005
Subtitle of host publicationIEEE International Geoscience and Remote Sensing Symposium
Pages5622-5625
Number of pages4
DOIs
StatePublished - Dec 1 2005
Event2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005 - Seoul, Korea, Republic of
Duration: Jul 25 2005Jul 29 2005

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume8

Other

Other2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005
CountryKorea, Republic of
CitySeoul
Period7/25/057/29/05

Fingerprint

Semantics
modeling
Association rules
Interoperability
Data mining
Labels
method

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Shyu, C. R., Barb, A. S., & Davis, C. H. (2005). Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval. In 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium (pp. 5622-5625). [1526051] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 8). https://doi.org/10.1109/IGARSS.2005.1526051
Shyu, Chi Ren ; Barb, Adrian Sorin ; Davis, Curt H. / Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval. 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. pp. 5622-5625 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{3bad34f2d3ba4b9f887ede78720b0f62,
title = "Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval",
abstract = "Query methods using visual semantics play an important role in horizontal interoperability of geospatial databases. However, a common practice is to manually label visual semantics of images using text annotations. This approach is subjective and, more importantly, impractical when dealing with large-scale geospatial image databases. In this paper, we propose a knowledge discovery (KDD) framework to link low-level image features with high-level visual semantics in an attempt to automate the process of retrieving semantically similar images. Our framework first extracts association rules that correlate semantic terms with discrete intervals of individual features. It then applies possibility functions to mathematically model visual semantics. Our approach provides a unique way to query image databases using semantics, and to potentially make available a knowledge exchange method for the geospatial community.",
author = "Shyu, {Chi Ren} and Barb, {Adrian Sorin} and Davis, {Curt H.}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IGARSS.2005.1526051",
language = "English (US)",
isbn = "0780390504",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
pages = "5622--5625",
booktitle = "25th Anniversary IGARSS 2005",

}

Shyu, CR, Barb, AS & Davis, CH 2005, Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval. in 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium., 1526051, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 8, pp. 5622-5625, 2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005, Seoul, Korea, Republic of, 7/25/05. https://doi.org/10.1109/IGARSS.2005.1526051

Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval. / Shyu, Chi Ren; Barb, Adrian Sorin; Davis, Curt H.

25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. p. 5622-5625 1526051 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 8).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval

AU - Shyu, Chi Ren

AU - Barb, Adrian Sorin

AU - Davis, Curt H.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Query methods using visual semantics play an important role in horizontal interoperability of geospatial databases. However, a common practice is to manually label visual semantics of images using text annotations. This approach is subjective and, more importantly, impractical when dealing with large-scale geospatial image databases. In this paper, we propose a knowledge discovery (KDD) framework to link low-level image features with high-level visual semantics in an attempt to automate the process of retrieving semantically similar images. Our framework first extracts association rules that correlate semantic terms with discrete intervals of individual features. It then applies possibility functions to mathematically model visual semantics. Our approach provides a unique way to query image databases using semantics, and to potentially make available a knowledge exchange method for the geospatial community.

AB - Query methods using visual semantics play an important role in horizontal interoperability of geospatial databases. However, a common practice is to manually label visual semantics of images using text annotations. This approach is subjective and, more importantly, impractical when dealing with large-scale geospatial image databases. In this paper, we propose a knowledge discovery (KDD) framework to link low-level image features with high-level visual semantics in an attempt to automate the process of retrieving semantically similar images. Our framework first extracts association rules that correlate semantic terms with discrete intervals of individual features. It then applies possibility functions to mathematically model visual semantics. Our approach provides a unique way to query image databases using semantics, and to potentially make available a knowledge exchange method for the geospatial community.

UR - http://www.scopus.com/inward/record.url?scp=33745713768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745713768&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2005.1526051

DO - 10.1109/IGARSS.2005.1526051

M3 - Conference contribution

AN - SCOPUS:33745713768

SN - 0780390504

SN - 9780780390508

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 5622

EP - 5625

BT - 25th Anniversary IGARSS 2005

ER -

Shyu CR, Barb AS, Davis CH. Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval. In 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. p. 5622-5625. 1526051. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2005.1526051