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


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
Number of pages4
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


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

ASJC Scopus subject areas

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


Dive into the research topics of 'Finding objects in image databases by grouping'. Together they form a unique fingerprint.

Cite this