Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web

Marco La Cascia, Leonid Taycher, Stan Sclaroff, Saratendu Sethi

Risultato della ricerca: Article

107 Citazioni (Scopus)

Abstract

A system is proposed that combines textual and visual statistics in a single index vector for content-based search of a WWW image database. Textual statistics are captured in vector form using latent semantic indexing based on text in the containing HTML document. Visual statistics are captured in vector form using color and orientation histograms. By using an integrated approach, it becomes possible to take advantage of possible statistical couplings between the content of the document (latent semantic content) and the contents of images (visual statistics). The combined approach allows improved performance in conducting content-based search. Search performance experiments are reported for a database containing 350,000 images collected from the WWW.
Lingua originaleEnglish
pagine (da-a)86-98
Numero di pagine13
RivistaComputer Vision and Image Understanding
Volume75
Stato di pubblicazionePublished - 1999

Fingerprint

Image retrieval
World Wide Web
Statistics
Semantics
HTML
Color
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cita questo

Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web. / La Cascia, Marco; Taycher, Leonid; Sclaroff, Stan; Sethi, Saratendu.

In: Computer Vision and Image Understanding, Vol. 75, 1999, pag. 86-98.

Risultato della ricerca: Article

@article{cca4a37e4aff43538e9667650ceb17c5,
title = "Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web",
abstract = "A system is proposed that combines textual and visual statistics in a single index vector for content-based search of a WWW image database. Textual statistics are captured in vector form using latent semantic indexing based on text in the containing HTML document. Visual statistics are captured in vector form using color and orientation histograms. By using an integrated approach, it becomes possible to take advantage of possible statistical couplings between the content of the document (latent semantic content) and the contents of images (visual statistics). The combined approach allows improved performance in conducting content-based search. Search performance experiments are reported for a database containing 350,000 images collected from the WWW.",
keywords = "CBIR, latent semantic indexing",
author = "{La Cascia}, Marco and Leonid Taycher and Stan Sclaroff and Saratendu Sethi",
year = "1999",
language = "English",
volume = "75",
pages = "86--98",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web

AU - La Cascia, Marco

AU - Taycher, Leonid

AU - Sclaroff, Stan

AU - Sethi, Saratendu

PY - 1999

Y1 - 1999

N2 - A system is proposed that combines textual and visual statistics in a single index vector for content-based search of a WWW image database. Textual statistics are captured in vector form using latent semantic indexing based on text in the containing HTML document. Visual statistics are captured in vector form using color and orientation histograms. By using an integrated approach, it becomes possible to take advantage of possible statistical couplings between the content of the document (latent semantic content) and the contents of images (visual statistics). The combined approach allows improved performance in conducting content-based search. Search performance experiments are reported for a database containing 350,000 images collected from the WWW.

AB - A system is proposed that combines textual and visual statistics in a single index vector for content-based search of a WWW image database. Textual statistics are captured in vector form using latent semantic indexing based on text in the containing HTML document. Visual statistics are captured in vector form using color and orientation histograms. By using an integrated approach, it becomes possible to take advantage of possible statistical couplings between the content of the document (latent semantic content) and the contents of images (visual statistics). The combined approach allows improved performance in conducting content-based search. Search performance experiments are reported for a database containing 350,000 images collected from the WWW.

KW - CBIR, latent semantic indexing

UR - http://hdl.handle.net/10447/38566

M3 - Article

VL - 75

SP - 86

EP - 98

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -