TY - GEN
T1 - Deep BLSTM neural networks for unconstrained continuous handwritten text recognition
AU - Frinken, Volkmar
AU - Uchida, Seiichi
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/11/20
Y1 - 2015/11/20
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84962480779&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962480779&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2015.7333894
DO - 10.1109/ICDAR.2015.7333894
M3 - Conference contribution
AN - SCOPUS:84962480779
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 911
EP - 915
BT - 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
PB - IEEE Computer Society
T2 - 13th International Conference on Document Analysis and Recognition, ICDAR 2015
Y2 - 23 August 2015 through 26 August 2015
ER -