Multi-linguistic handwritten character recognition by Bayesian decision-based neural networks

This paper proposes a multi-linguistic handwritten characters recognition system based on Bayesian decision-based neural networks (BDNN). The proposed system consists of two modules: first, a coarse classifier determines an input character to one of the pre-defined subclasses partitioned from a large character set, such as Chinese mixed with alphanumerics. Then a character recognizer determines the input image to its most matched reference character in the subclass. The proposed BDNN can be effectively applied to implement all these modules. It adopts a hierarchical network structures with nonlinear basis functions and a competitive credit-assignment scheme. Our prototype system demonstrates a successful utilization of BDNN to handwriting of Chinese and alphanumeric character recognition on both the public databases (HCCR/CCL for Chinese and CEDAR for the alphanumerics) and in house database (NCTU/NNL). Regarding the performance, experiments on three different databases all demonstrated high recognition (88/spl sim/92%) accuracies as well as low rejection/acceptance (6.7%) rates. As to the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27 second/character on a Pentium-90 based personal computer, without using hardware accelerator or co-processor.