Modified Radial Basis Function and Orthogonal Bipolar Vector for Better Performance of Pattern Recognition

This work proposes the use of orthogonal bipolar vectors (OBV) as new target vectors for Artificial Neural Networks (ANN) of the Radial Basis Functions (RBF) type for pattern recognition problems. The network was trained and tested with three sets of biometric data: human iris, handwritten digits and signs of the Australian sign language, Auslan. The objective was to verify the network performance with the use of OBVs and to compare the results obtained with those presented for the Multilayer Perceptron (MLP) networks. Datasets used in the experiments were obtained from the CASIA Iris Image Database developed by the Chinese Academy of Sciences - Institute of Automation, Semeion Handwritten Digit of Machine Learning Repository and UCI Machine Learning Repository. The networks were modeled using OBVs and conventional bipolar vectors for comparing the results. The classification of the patterns in the output layer was based on the Euclidean distance. The results show that the use of OBVs in the network training process improved the hit rate and reduced the amount of epochs required for convergence.