Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

Recognition of Images in Large Databases Using a Learning Framework

Serge Belongie, Chad Carson, Hayit Greenspan and Jitendra Malik

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-97-939
April 1997

http://www.eecs.berkeley.edu/Pubs/TechRpts/1997/CSD-97-939.pdf

Retrieving images from very large collections using image content as a key is becoming an important problem. Classifying images into visual categories and finding objects in image databases are two major challenges in the field. This paper describes our approach toward the first of the two tasks, the generalization of which we believe will assist in the second task as well.

We define a blobworld representation which provides a transition from the raw pixel data to a small set of localized coherent regions in color and texture space. Learning is then utilized to extract a probabilistic interpretation of the scene. Experimental results are presented for more than 1000 images from the Corel photo collection.


BibTeX citation:

@techreport{Belongie:CSD-97-939,
    Author = {Belongie, Serge and Carson, Chad and Greenspan, Hayit and Malik, Jitendra},
    Title = {Recognition of Images in Large Databases Using a Learning Framework},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1997},
    Month = {Apr},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1997/5228.html},
    Number = {UCB/CSD-97-939},
    Abstract = {Retrieving images from very large collections using image content as a key is becoming an important problem. Classifying images into visual categories and finding objects in image databases are two major challenges in the field. This paper describes our approach toward the first of the two tasks, the generalization of which we believe will assist in the second task as well. <p>We define a blobworld representation which provides a transition from the raw pixel data to a small set of localized coherent regions in color and texture space. Learning is then utilized to extract a probabilistic interpretation of the scene. Experimental results are presented for more than 1000 images from the Corel photo collection.}
}

EndNote citation:

%0 Report
%A Belongie, Serge
%A Carson, Chad
%A Greenspan, Hayit
%A Malik, Jitendra
%T Recognition of Images in Large Databases Using a Learning Framework
%I EECS Department, University of California, Berkeley
%D 1997
%@ UCB/CSD-97-939
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1997/5228.html
%F Belongie:CSD-97-939