CALL FOR PAPERS 
IEEE Transactions on Pattern Analysis and Machine Intelligence 

SPECIAL ISSUE on 
Perceptual Organization in Computer Vision 
(Submission Deadline: December 15, 2001) 

Guest Editors: 
David Jacobs, NEC Research Institute, dwj@research.nj.nec.com 
Michael Lindenbaum, Technion, mic@cs.technion.ac.il 

As recognized by the Gestalt school, the importance of perceptual 
organization (PO) in human vision cannot be overestimated; it imparts 
both efficiency and robustness to the visual process. Since early 
demonstrations in the 1980s underscored its usefulness in object 
recognition, the computer vision community has seen various applications 
of PO in artificial vision systems such as in stereo matching, model 
indexing, contour completion, figure-ground segmentation, change 
detection, and more. Indeed, it can be argued that a reasonable 
computational model of perception can be built around the notion of 
repeated detection and classification of organized structure. 

Papers are solicited that address a wide range of issues in the 
computational understanding of perceptual organization. Appropriate 
domains include, but are not limited to: Computational modeling of human 
performance on psychophysical stimuli (eg., illusory contours); 
Segmentation or grouping in single natural images; Building intermediate 
image descriptions such as skeletons; Segmentation of medical or other 
non-visual imagery; Segmentation in video of independently moving 
objects; Performance assessment and prediction of grouping perceptual 
organization algorithms. Relevant techniques for perceptual 
organization include, but are not limited to: Graph-based algorithms 
including spectral methods; Search algorithms; Techniques from learning 
including E-M, belief propagation, and Markov Chain Monte Carlo methods; 
Level set methods. 

Our focus will be on computational methods of perceptual organization. 
Therefore, the focus of each paper should be on these issues. For 
example, papers should not primarily focus on presenting psychological 
data or generic optimization techniques. However, we will also welcome 
tutorial or review papers designed to bring to attention relevant work 
from related communities, such as visual psychology, graph theory, 
optimization, and learning. If authors are concerned whether their 
paper would fall within the scope of this special issue, please send an 
abstract/proposal to the editors for a preliminary evaluation prior to 
the due date. 

All submitted papers will be reviewed according to the guidelines and 
standards of PAMI. We prefer that authors submit electronic versions of 
their papers in postscript or pdf. Alternately, authors may submit=20 
four hardcopies of their papers. Submissions should be sent to: 
Prof. Michael Lindenbaum, Computer Science Dept. 
Technion, Haifa 32000, Israel 
mailto:mic@cs.technion.ac.il 

Manuscripts are to be submitted by 15 December 2001. First reviews 
should be returned to authors around the middle of March, 2002. Revised 
Manuscripts will be due by the end of June. The special issue should 
appear in an issue of PAMI near the end of 2002.