Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models

作者：

Highlights：

• We evaluate comprehensively neural network language models (NNLMs) and hybrid NNLMs in handwritten Chinese text recognition.

• We apply CNNs to over-segmentation and geometric context modeling in addition to character recognition.

• By training NNLMs on large corpus and integrating CNN shape models, we achieve new state-of-the-art performance on standard datasets.

• We analyze the upper bound of performance of the text recognition system by calculating the lattice error rate.

摘要

Highlights•We evaluate comprehensively neural network language models (NNLMs) and hybrid NNLMs in handwritten Chinese text recognition.•We apply CNNs to over-segmentation and geometric context modeling in addition to character recognition.•By training NNLMs on large corpus and integrating CNN shape models, we achieve new state-of-the-art performance on standard datasets.•We analyze the upper bound of performance of the text recognition system by calculating the lattice error rate.

论文关键词：Handwritten Chinese text recognition,Feedforward neural network language model,Recurrent neural network language model,Hybrid language model,Convolutional neural network shape models

论文评审过程：Received 26 February 2016, Revised 23 December 2016, Accepted 24 December 2016, Available online 29 December 2016, Version of Record 6 January 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.12.026