SPECIAL ISSUE of IMAGE and VISION COMPUTING JOURNAL

				on

          Evolutionary Computation in Computer Vision
	 ---------------------------------------------
			 Call for Papers
			-----------------


Theme of the Special Issue 

Evolutionary computation is a term used to encompass
a variety of population-based problem solving techniques
that mimic the natural process of Darwinian evolution. Current
research in evolutionary computation has resulted in powerful, yet
versatile problem solving mechanisms for searching, adaptation,
learning and optimization in a variety of application domains.
The main avenues for research in evolutionary computation are
genetic algorithms, genetic programming, evolutionary strategies and
evolutionary programming. Genetic algorithms stress chromosomal
operators, genetic programming deals with operators on
more general hierarchical structures, evolution strategies
emphasize behavioral changes at the level of the individual
whereas evolutionary programming stresses behavioral changes at the
level of the species. The common factor underlying all the above
approaches to evolutionary computation is the emphasis on an
ensemble of solution structures, and the evaluation and
evolution of these structures via specialized operators that mimic
their biological counterparts, in response to an ever changing
environment.

Problems in computer vision and image understanding have
always called for powerful problem solving techniques. This special
issue will focus on problem solving techniques for computer vision and
image understanding that are based on the paradigm of evolutionary
computation. The topics of relevance to the special issue include
but are not necessarily limited to:

Low-level vision

Evolutionary optimization, adaptation
and learning algorithms for edge detection, image segmentation,
figure-ground separation, texture analysis, feature selection,
shape-from-XYZ and surface reconstruction.

High-level vision

Evolutionary computation for object
recognition, scene analysis, indexing and search of model/image
databases, and high-level learning of symbolic descriptions.

Active vision

Evolutionary computation for autonomous
vision-guided navigation, path planning, sensing strategies, sensor
integration, visual servoing, vergence and gaze control, hand-eye
coordination, active tracking and vision-guided task planning.

Neural vision

Evolutionary computation for learning,
adaptation and optimization of neural network structure and topology
for computer vision problems.


Guest Editor

Dr. Suchendra M. Bhandarkar
Department of Computer Science
415 Boyd Graduate Studies Research Center
The University of Georgia
Athens, GA 30602-7404, U.S.A.
Telephone: (706) 542-1082
FAX: (706) 542-2966 
E-mail: suchi@cs.uga.edu

Submission Procedure


Five copies of manuscripts (not exceeding 35 double-spaced pages
in 12 pt size font including figures and tables) describing previously
unpublished and original research should be submitted to reach the
guest editor on or before January 31, 1997. All submissions will be
peer reviewed for originality, significance, technical content and
relevance to the special issue.