Abstract | ||
---|---|---|
Recently, two different trends in neural network-based machine learning could be observed. The first one are the introduction of Bidirectional Long Short-Term Memory (BLSTM) neural networks (NN) which made sequences with long-distant dependencies amenable for neural network-based processing. The second one are deep learning techniques, which greatly increased the performance of neural networks, by making use of many hidden layers. In this paper, we propose to combine these two ideas for the task of unconstrained handwriting recognition. Extensive experimental evaluation on the IAM database demonstrate an increase of the recognition performance when using deep learning approaches over commonly used BLSTM neural networks, as well as insight into how different types of hidden layers affect the recognition accuracy. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICDAR.2015.7333894 | International Conference on Document Analysis and Recognition |
Field | DocType | ISSN |
Computer science,Recurrent neural network,Handwriting recognition,Speech recognition,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Text recognition | Conference | 1520-5363 |
Citations | PageRank | References |
5 | 0.44 | 16 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Volkmar Frinken | 1 | 607 | 30.01 |
Seiichi Uchida | 2 | 790 | 105.59 |