Eran Borenstein

Eran Borenstein Mathematical Sciences Research Institute 1725 Telegraph Ave. Berkeley CA 94703 Telephone: (510)-643-6062

I am currently an MSRI member, participating in the Mathematical, Computational and Statistical Aspects of Image Analysis.
I am also a post-doc at the EECS department in UC Berkeley, working with Jitendra Malik.
I performed my doctoral studies in the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science, with Shimon Ullman.

My research area is machine and human vision. My aim is to conduct research designed to better understand and imitate the processes of the human visual system, and examine their potential implementation in computer vision as well as possible applications. I wish to focus on developing models that account for the ability of our visual system to know "what" is in the image and "where" it is. In particular, I am interested in object classification and recognition, figure-ground segmentation, the interaction between top-down and bottom-up visual processes and other problems related to perceptual organization.

• Combining Top-down and Bottom-up Segmentation
  (abstract)
  E. Borenstein, E. Sharon and S. Ullman
  Proceedings IEEE workshop on Perceptual Organization in Computer Vision
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2004
  
  
• Learning to Segment
  (abstract)
  E. Borenstein and S. Ullman
  Springer-Verlag LNCS 3023
  European Conference on Computer Vision (ECCV), May 2004
  
  
• Class-Specific, Top-Down Segmentation
  (abstract)
  E. Borenstein and S. Ullman
  Springer-Verlag LNCS 2351
  European Conference on Computer Vision (ECCV), May 2002
  
  
• Lightness and Brightness Computations by Retinex-like Algorithms
  (abstract)
  Thesis for my M.Sc degree with Shimon Ullman
  Weizmann Institute of Science 2000
  
  

Horse Images

The Weizmann Horse Database consists of 328 side-view color images of horses that were also manually segmented. The images were randomly collected from the WWW to evaluate the top-down segmentation scheme as well as its combination with bottom-up processing. For further elaboration, please refer to our related publications above (ECCV2002, ECCV2004,CVPR2004).
Please feel free to download and use this database, providing you reference one of the above papers.

Entire database (19.5Mb) including:
Horses (RGB) (14Mb)
Horses (grey) (4Mb)
Horses (figure-ground) (1.3Mb)