IDEALS Home University of Illinois at Urbana-Champaign logo The Alma Mater The Main Quad

Finding Pictures of Objects in Large Collections of Images

Show full item record

Bookmark or cite this item: http://hdl.handle.net/2142/25948

Files in this item

File Description Format
PDF Forsyth_Finding.pdf (12MB) (no description provided) PDF
Title: Finding Pictures of Objects in Large Collections of Images
Author(s): Forsyth, David A.; Leung, Thomas K.; Bregler, Chris; Carson, C.; Greenspan, H.; Fleck, Margaret M.
Subject(s): Digital Libraries electronic information resources digital images image access image retrieval detection rules grouping rules image segmentation visual primatives
Abstract: "Retrieving images from very large collections using image content as a key is becoming an important problem. Users prefer to ask for pictures using notions of content that are strongly oriented to the presence of objects, which are quite abstractly defined. Computer programs that implement these queries automatically are desirable but are hard to build be-cause conventional object recognition techniques from computer vision cannot recognize very general objects in very general contexts. This paper describes an approach to object recognition structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints. The constraints that are satisfied provide a form of object classification in quite general contexts. This view of recognition is distinguished by far richer involvement of early visual primitives, including color and texture; the ability to deal with rather general objects in uncontrolled configurations and contexts; and a satisfactory notion of classification. These properties are illustrated with three case studies: one demonstrates the use of descriptions that fuse color and spatial properties; one shows how trees can be de-scribed by fusing texture and geometric properties; and one shows how this view of recognition yields a program that can tell, quite accurately, whether a picture contains naked people or not."
Issue Date: 1997
Publisher: Graduate School of Library and Information Science, University of Illinois at Urbana-Champaign
Citation Info: Forsyth, David A. ; Malik,Jitendra ; Leung,Thomas K. ; Bregler,Chris ; Carson,C. ; Greenspan,H. ; Fleck, Margaret M. (1997) Finding Pictures of Objects in Large Collections of Images. In P. Bryan Heidorn; Beth Sandore (Eds.) (1997) Digital Image Access & Retrieval [papers presented at the 1996 Clinic on Library Applications of Data Processing, March 24-26, 1996 Urbana-Champaign] : Graduate School of Library and Information Science, University of Illinois at Urbana-Champaign: 118-139.
Series/Report: Digital Image Access & Retrieval [papers presented at the 1996 Clinic on Library Applications of Data Processing, March 24-26, 1996 Urbana-Champaign]
Genre: Conference Paper / Presentation
Type: Text
Language: English
URI: http://hdl.handle.net/2142/25948
ISBN: 0-87845-100-5
ISSN: 0069-4789
Publication Status: published or submitted for publication
Date Available in IDEALS: 2011-08-17
 

This item appears in the following Collection(s)

Show full item record

Item Statistics

  • Total Downloads: 261
  • Downloads this Month: 12
  • Downloads Today: 1

Browse

My Account

Information

Access Key