Special Issue on Agent based Computer Vision
Guest Editors: Dr. Paul Rosin and Dr. Omer Rana, University of Cardiff
Submission Deadline: 31st October 2002
Vision is one of the most important sources of information for supporting intelligent human behaviour, as well as a key competence for designing new types of intelligent computers and machines. Over the period of the past 40 years or so, computer vision has evolved into a mature subject including many topics and applications which range from the automatic interpretation of documents to the image recognition for the automatic guidance of vehicles. In reality, however, current computer vision systems are vastly different from, and in most ways inferior to, biological vision systems.
Software agents are computer programs capable of flexible, autonomous action -- and may support a wide range of different behaviours, defined as rules, or based on machine learning algorithms such as neural networks. Agents also, generally, monitor their operating environment and respond to events in a timely fashion, utilising internal scheduling and planning engines to formulate a response. Perhaps the most significant advantage that an agent based approach provides is the ability to design systems based on decoupled units -- based on the particular role that such a unit is likely to play within a multi-agent system.
Authors are encouraged to submit papers which cover some of the following issues (although this list is by no means exhaustive):
Authors are encouraged to submit their manuscripts (there is no length limit on the initial submission) to either: Paul.Rosin@cs.cf.ac.uk or firstname.lastname@example.org by electronic mail (preferred) in PDF or PostScript. The paper should be formatted to print on A4 paper, using a minimum of 12pt font size. Surface mail submissions are also welcome; please send three copies of your paper to Dr. Paul Rosin or Dr. Omer Rana at
Department of Computer Science,
PO Box 916,
||31st October 2002|