Improvements on handwritten digit recognition by cooperation of modular neural networks

In this paper modular neural networks are used to improve handwritten digit recognition. To evaluate the performance of modular networks, a comparison is made with a global neural network, on the same database. Two basic kind of modular networks are considered. In the first one, seven expert modular networks are used. Five of them are provided for digits 0, 1, 2, 5, 6, 7. The other two modular networks are for the pair of digits 3-8 and 4-9 respectively. The second kind of modular neural network considers an expert module for each feature extracted from the handwritten digit image. The cooperation is among modules extracting slope and radial projection from each digit. Two type of cooperation among modular networks are considered: neural network and weighted combination of the modules outputs. The models were trained with a set of 1.837 handwritten digits, tested on a different set of 918 digits where the best weight set was selected for each neural network, and finally results were validated on a different set of 919 digits. Results show that by using modular network for features, it is possible to improve classification performance on handwritten digits, from 91.0% in the case of global networks to 93.5% of modular networks.