Condensing image databases when retrieval is based on non-metric distances

David W. Jacobs; Daphna Weinshall; Yoram Gdalyahu

Condensing image databases when retrieval is based on non-metric distances

David W. Jacobs^*, Daphna Weinshall, Yoram Gdalyahu

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

12 Scopus citations

Abstract

One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance often make use of similarity judgements that are non-metric. Existing condensing techniques for finding class representatives which are ill-suited to deal with non-metric dataspaces are presented. The importance of ideas learned from the experience of improving performance using both synthetic and real images are discussed.

Original language	English
Pages	596-601
Number of pages	6
State	Published - 1998
Externally published	Yes
Event	Proceedings of the 1998 IEEE 6th International Conference on Computer Vision - Bombay, India Duration: 4 Jan 1998 → 7 Jan 1998

Conference

Conference	Proceedings of the 1998 IEEE 6th International Conference on Computer Vision
City	Bombay, India
Period	4/01/98 → 7/01/98

Cite this

@conference{4609d93b8df849a0a3975581dee87db3,

title = "Condensing image databases when retrieval is based on non-metric distances",

abstract = "One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance often make use of similarity judgements that are non-metric. Existing condensing techniques for finding class representatives which are ill-suited to deal with non-metric dataspaces are presented. The importance of ideas learned from the experience of improving performance using both synthetic and real images are discussed.",

author = "Jacobs, {David W.} and Daphna Weinshall and Yoram Gdalyahu",

year = "1998",

language = "אנגלית",

pages = "596--601",

note = "Proceedings of the 1998 IEEE 6th International Conference on Computer Vision ; Conference date: 04-01-1998 Through 07-01-1998",

}

TY - CONF

T1 - Condensing image databases when retrieval is based on non-metric distances

AU - Jacobs, David W.

AU - Weinshall, Daphna

AU - Gdalyahu, Yoram

PY - 1998

Y1 - 1998

N2 - One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance often make use of similarity judgements that are non-metric. Existing condensing techniques for finding class representatives which are ill-suited to deal with non-metric dataspaces are presented. The importance of ideas learned from the experience of improving performance using both synthetic and real images are discussed.

AB - One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performance often make use of similarity judgements that are non-metric. Existing condensing techniques for finding class representatives which are ill-suited to deal with non-metric dataspaces are presented. The importance of ideas learned from the experience of improving performance using both synthetic and real images are discussed.

UR - http://www.scopus.com/inward/record.url?scp=0032316166&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:0032316166

SP - 596

EP - 601

T2 - Proceedings of the 1998 IEEE 6th International Conference on Computer Vision

Y2 - 4 January 1998 through 7 January 1998

ER -

Condensing image databases when retrieval is based on non-metric distances

Abstract

Conference

Other files and links

Fingerprint

Cite this