This paper applies Convolutional Neural Networks (CNNs) for offline handwritten English character recognition. We use a modified LeNet-5 CNN model, with special settings of the number of neurons in each layer and the connecting way between some layers. Outputs of the CNN are set with error-correcting codes, thus the CNN has the ability to reject recognition results. For training of the CNN, an error-samples-based reinforcement learning strategy is developed. Experiments are evaluated on UNIPEN lowercase and uppercase datasets, with recognition rates of 93.7% for uppercase and 90.2% for lowercase, respectively.
展开▼
