Title | ||
---|---|---|
Offline Handwritten English Character Recognition Based on Convolutional Neural Network |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/DAS.2012.61 | Document Analysis Systems |
Keywords | Field | DocType |
offline handwritten english character,uppercase datasets,recognition rate,convolutional neural networks,special setting,modified lenet-5 cnn model,error-samples-based reinforcement,error-correcting code,unipen lowercase,recognition result,convolutional neural network,learning artificial intelligence,neural network,feature extraction,neural nets,error correction code,convolutional codes,error correcting code,reinforcement learning | Convolutional code,Character recognition,Pattern recognition,Computer science,Convolutional neural network,Speech recognition,Error detection and correction,Feature extraction,Artificial intelligence,Artificial neural network,Reinforcement learning | Conference |
Citations | PageRank | References |
10 | 0.58 | 7 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aiquan Yuan | 1 | 18 | 1.15 |
Gang Bai | 2 | 11 | 2.65 |
Lijing Jiao | 3 | 10 | 0.58 |
Yajie Liu | 4 | 19 | 3.31 |