Apply the combination of multiple classifiers with the SGNG algorithm for Thai printed character recognition

This paper studies the combination of multiple classifiers with a prototyped-based supervised clustering algorithm, namely SGNG, for Thai printed character recognition. The proposed classification system consists of two steps. First, the prototypes obtained by the SGNG are firstly used to roughly classify an unknown input positioning around a training dataset. Second, several classifiers, such as Bayesian classifiers and neural network, are combined by using the median rule for detail classification. Our experimental result shows that the combination of multiple classifiers gives recognition rates better that individual classifier. In particularly, the combination of multiple classifiers with the SGNG can improve accuracy of recognition rates and classification time.