Abstract: This lecture is an approach dedicated to the improvement of color pattern recognition performances for computer vision. Like humans, the artificial intelligence systems use color for pattern recognition. There are a lot of systems for pictorial content representation and recognition based on color features. First section is dedicated to the evaluation of the color spaces for computer vision. One considers the conversion from the conventional RGB space into a color space with improved pattern recognition performances. In the second section, we present the model of Concurrent Neural Classifiers (CNC) representing a collection of small neural networks, which use a global winner-takes-all strategy. Each neural module is trained to correctly classify the patterns of one class only and the number of modules equals the number “M” of classes. One considers the case of choosing the SOM (Self-Organized-Map) as a neural module. We built “M” training pattern sets and each neural module is trained with the pattern set characterized by the corresponding class label. Third section has as theme data fusion for color pattern recognition as an emerging technology with significant advantages over simple source data . We consider data fusion and feature fusion for the channels of the considered color space. Fourth section is dedicated to the special technique of pattern recognition called decision fusion, by combining the classification powers of several classifiers. The combination function should take advantage of the strengths of the individual classifiers, avoid their weaknesses, and improve classification accuracy. We present the experimental results of our approach for color pattern recognition in the fields of biometrics and robotics.

Brief Biography of the Speaker:
Dr. Victor-Emil Neagoe is a Professor of the Department of Electronics, Telecommunications, and Information Technology at the Polytechnic University of Bucharest, Romania.
He teaches the following courses : Pattern Recognition and Artificial Intelligence; Digital Signal Processing; Computational Intelligence ; Detection and Estimation for Information Processing. He co-ordinates 10 Ph.D. candidates.His research interest corresponds to the fields of pattern recognition, computational intelligence, biometric technology , satellite image analysis and sampling theory. Prof. Neagoe is author of more than 120 published papers.His has internationally recognized results concerning concurrent self-organized maps, face recognition, optimum color conversion, syntactical self-organized maps, nonuniform sampling theorems, inversion of the Van der Monde matrix, predictive ordering and linear approximation for image data compression, Legendre descriptors for classification of polygonal closed curves.
He has been included in Who’s Who in the World and Europe 500 and he has been nominated by the American Biographical Institute for American Medal of Honor and for World Medal of Honor. He has been a Member IEEE since 1978 and a Senior Member IEEE since 1984. He has been a plenary speaker for several WSEAS conferences since 2006 till 2009.