Neural network language models for off-line handwriting recognition

作者：

Highlights：

• We study the use of neural network language models for two state-of-the-art recognizers for unconstrained off-line HTR.

• We found consistent improvement when using this language model, combined or not with standard N-grams language models.

• The neural network language model scales well with different dictionary sizes for the IAM-DB task.

• By combining the two recognition systems, unprecedented accuracy for the IAM database is reported.

摘要

Highlights•We study the use of neural network language models for two state-of-the-art recognizers for unconstrained off-line HTR.•We found consistent improvement when using this language model, combined or not with standard N-grams language models.•The neural network language model scales well with different dictionary sizes for the IAM-DB task.•By combining the two recognition systems, unprecedented accuracy for the IAM database is reported.

论文关键词：Handwritten text recognition (HTR),Language models (LMs),Neural networks (NNs),Neural network language model (NN LM),Bidirectional long short-term memory neural networks (BLSTM),Hybrid HMM/ANN models,ROVER combination

论文评审过程：Received 5 November 2012, Revised 17 August 2013, Accepted 22 October 2013, Available online 4 November 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.10.020