Computer vision tools for finding images and video sequences

Research output: Contribution to journalArticle

Abstract

VERY LARGE COLLECTIONS OF IMAGES are now common. Indexing and searching such collections using indexing languages is difficult. Computer vision offers a variety of techniques for searching for pictures in large collections. Appearance methods compare images based on the overall content of the image using such criteria as similarity of color histograms, texture histograms, spatial layout, and filtered representations. Finding methods concentrate on matching subparts of images, defined in a variety of ways, in the hope of finding particular objects. These ideas are illustrated with a variety of examples from the current literature.

Original languageEnglish (US)
Pages (from-to)326-355
Number of pages30
JournalLibrary Trends
Volume48
Issue number2
StatePublished - Sep 1 1999
Externally publishedYes

Fingerprint

video
indexing
layout
language

ASJC Scopus subject areas

  • Library and Information Sciences

Cite this

Computer vision tools for finding images and video sequences. / Forsyth, D. A.

In: Library Trends, Vol. 48, No. 2, 01.09.1999, p. 326-355.

Research output: Contribution to journalArticle

@article{a897f5e7375a431189155171b45691ed,
title = "Computer vision tools for finding images and video sequences",
abstract = "VERY LARGE COLLECTIONS OF IMAGES are now common. Indexing and searching such collections using indexing languages is difficult. Computer vision offers a variety of techniques for searching for pictures in large collections. Appearance methods compare images based on the overall content of the image using such criteria as similarity of color histograms, texture histograms, spatial layout, and filtered representations. Finding methods concentrate on matching subparts of images, defined in a variety of ways, in the hope of finding particular objects. These ideas are illustrated with a variety of examples from the current literature.",
author = "Forsyth, {D. A.}",
year = "1999",
month = "9",
day = "1",
language = "English (US)",
volume = "48",
pages = "326--355",
journal = "Library Trends",
issn = "0024-2594",
publisher = "Johns Hopkins University Press",
number = "2",

}

TY - JOUR

T1 - Computer vision tools for finding images and video sequences

AU - Forsyth, D. A.

PY - 1999/9/1

Y1 - 1999/9/1

N2 - VERY LARGE COLLECTIONS OF IMAGES are now common. Indexing and searching such collections using indexing languages is difficult. Computer vision offers a variety of techniques for searching for pictures in large collections. Appearance methods compare images based on the overall content of the image using such criteria as similarity of color histograms, texture histograms, spatial layout, and filtered representations. Finding methods concentrate on matching subparts of images, defined in a variety of ways, in the hope of finding particular objects. These ideas are illustrated with a variety of examples from the current literature.

AB - VERY LARGE COLLECTIONS OF IMAGES are now common. Indexing and searching such collections using indexing languages is difficult. Computer vision offers a variety of techniques for searching for pictures in large collections. Appearance methods compare images based on the overall content of the image using such criteria as similarity of color histograms, texture histograms, spatial layout, and filtered representations. Finding methods concentrate on matching subparts of images, defined in a variety of ways, in the hope of finding particular objects. These ideas are illustrated with a variety of examples from the current literature.

UR - http://www.scopus.com/inward/record.url?scp=0033264223&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033264223&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033264223

VL - 48

SP - 326

EP - 355

JO - Library Trends

JF - Library Trends

SN - 0024-2594

IS - 2

ER -