Thesis CTDIA prize

The Academic Dalcimar Casanova won the second best dissertation in the field of Artificial Intelligence. The prize was awarded by the Special Committee on Artificial Intelligence of the Brazilian Computer Society (SBC-CEIA) during the 2010 Joint Conference.

To read more visit: VII Best MSc Dissertation/PhD Thesis Contest in Artificial Intelligence

Sigma ynergos - Synergetic vision research

OM Bruno and RM Cesar and LA Consularo and LD Costa

REAL-TIME SYSTEMS, 21(1-2):7-41, 2001

This paper reports the development of a powerful and versatile laboratory for vision research, namely Sigma ynergos, which has been developed and implemented under Delphi/Windows in a distributed systems of microcomputers. The main paradigm underlying the whole approach consists in integrating several concepts and techniques into a single computing environment, i.e. Sigma ynergos, in such a way that the requisites and possibilities of each of the constituent components complement one another and the thus obtained result becomes greater than the sum of its parts. The components of Sigma ynergos include distributed system capabilities and a number of libraries containing algorithms for: computer vision, modeling and simulation of biological visual systems, data and classification analysis, software validation and comparative evaluation, Internet, off-the-shelf application, image databases, artificial intelligence, data mining, and visualization resources. In this paper special emphasis is placed upon the Internet, distributed implementation and biological vision. After outlining the principal requisites and potentials underlying each of such components, some specific situations of interest arising from the integration of two or more of such elements are described and discussed. Details concerning the integration with Internet and the implementation of the laboratory as a distributed system are provided, and a complete case-example is presented. This applications regards the implementation of a psychophysical experiment aimed at investigating human perception of pictorial complexity, including the derivation of a mathematic-computational framework modeling such a perception as well as the use of the Internet as a source of stimuli and for reporting the obtained results. In addition, the mathematic-computational model is derived by using a parallel version of the genetic algorithm running on the distributed system of PCs. The obtained encouraging results substantiate the potential of this vision laboratory for multidisciplinary vision research.