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

详细信息    查看全文

• 作者：Yi-Chao Wu^a ; ^{yichao.wu@nlpr.ia.ac.cn}Author Vitae ; Fei Yin^a ; ^{fyin@nlpr.ia.ac.cn}Author Vitae ; Cheng-Lin Liu^a ; ^b ; ^c ; ^{liucl@nlpr.ia.ac.cn}Author Vitae
• 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
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：65
• 期：Complete
• 页码：251-264
• 全文大小：1290 K
• 卷排序：65

文摘

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.