Cristian Molder

Perspective Correction For Image Processing

Abstract The paper proposes an algorithm for applying the perspective correction of images containing human faces. Based on the coordinates of the two eyes, of the center of the mouth and of a point on the line of the mouth, one can estimate the angle of inclination of the face. After applying the perspective correction, the area corresponding to the face can be used by a face recognition algorithm based on aspect in order to improve the good recognition rate.

An optimal full-genetic technique used to train RBF neural networks

It is well-known that, the pattern recognition performances assigned to RBF neural networks depends a lot by their specific training algorithms, and by the methods used for RBF center selection (e.g., a clustering technique), particularly. Having as starting point the membership of genetic algorithms to the powerful class of global optimization methods, an optimal full-genetic training procedure of RBF neural networks based on hybrid genetic clustering algorithm used for center mapping, and on genetic approach to fit the output neural weights is proposed. Finally, using a real pattern recognition task, a comparative study (as performance level) with others standard RBF training methods and SART neural network is also described.