Finding objects in image databases by grouping

J. Malik, David Alexander Forsyth, Margaret M Fleck, H. Greenspan, T. Leung, C. Carson, S. Belongie, C. Bregler

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

Abstract

Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. This paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case-studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
Editors Anon
PublisherIEEE
Pages761-764
Number of pages4
Volume2
StatePublished - 1996
Externally publishedYes
EventProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz
Duration: Sep 16 1996Sep 19 1996

Other

OtherProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)
CityLausanne, Switz
Period9/16/969/19/96

Fingerprint

Textures
Color
Object recognition

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Malik, J., Forsyth, D. A., Fleck, M. M., Greenspan, H., Leung, T., Carson, C., ... Bregler, C. (1996). Finding objects in image databases by grouping. In Anon (Ed.), IEEE International Conference on Image Processing (Vol. 2, pp. 761-764). IEEE.

Finding objects in image databases by grouping. / Malik, J.; Forsyth, David Alexander; Fleck, Margaret M; Greenspan, H.; Leung, T.; Carson, C.; Belongie, S.; Bregler, C.

IEEE International Conference on Image Processing. ed. / Anon. Vol. 2 IEEE, 1996. p. 761-764.

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

Malik, J, Forsyth, DA, Fleck, MM, Greenspan, H, Leung, T, Carson, C, Belongie, S & Bregler, C 1996, Finding objects in image databases by grouping. in Anon (ed.), IEEE International Conference on Image Processing. vol. 2, IEEE, pp. 761-764, Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3), Lausanne, Switz, 9/16/96.
Malik J, Forsyth DA, Fleck MM, Greenspan H, Leung T, Carson C et al. Finding objects in image databases by grouping. In Anon, editor, IEEE International Conference on Image Processing. Vol. 2. IEEE. 1996. p. 761-764
Malik, J. ; Forsyth, David Alexander ; Fleck, Margaret M ; Greenspan, H. ; Leung, T. ; Carson, C. ; Belongie, S. ; Bregler, C. / Finding objects in image databases by grouping. IEEE International Conference on Image Processing. editor / Anon. Vol. 2 IEEE, 1996. pp. 761-764
@inproceedings{52c11f7e66c54614a20f61738748189f,
title = "Finding objects in image databases by grouping",
abstract = "Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. This paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case-studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.",
author = "J. Malik and Forsyth, {David Alexander} and Fleck, {Margaret M} and H. Greenspan and T. Leung and C. Carson and S. Belongie and C. Bregler",
year = "1996",
language = "English (US)",
volume = "2",
pages = "761--764",
editor = "Anon",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE",

}

TY - GEN

T1 - Finding objects in image databases by grouping

AU - Malik, J.

AU - Forsyth, David Alexander

AU - Fleck, Margaret M

AU - Greenspan, H.

AU - Leung, T.

AU - Carson, C.

AU - Belongie, S.

AU - Bregler, C.

PY - 1996

Y1 - 1996

N2 - Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. This paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case-studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.

AB - Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. This paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case-studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.

UR - http://www.scopus.com/inward/record.url?scp=0030382464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030382464&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030382464

VL - 2

SP - 761

EP - 764

BT - IEEE International Conference on Image Processing

A2 - Anon, null

PB - IEEE

ER -