Integrated segmentation and recognition of handwritten numerals with cascade neural network

Abstract

In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.