当前位置: X-MOL 学术Int. J. Doc. Anal. Recognit. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A comprehensive study of hybrid neural network hidden Markov model for offline handwritten Chinese text recognition
International Journal on Document Analysis and Recognition ( IF 2.3 ) Pub Date : 2018-06-15 , DOI: 10.1007/s10032-018-0307-0
Zi-Rui Wang , Jun Du , Wen-Chao Wang , Jian-Fang Zhai , Jin-Shui Hu

This paper proposes an effective segmentation-free approach using a hybrid neural network hidden Markov model (NN-HMM) for offline handwritten Chinese text recognition (HCTR). In the general Bayesian framework, the handwritten Chinese text line is sequentially modeled by HMMs with each representing one character class, while the NN-based classifier is adopted to calculate the posterior probability of all HMM states. The key issues in feature extraction, character modeling, and language modeling are comprehensively investigated to show the effectiveness of NN-HMM framework for offline HCTR. First, a conventional deep neural network (DNN) architecture is studied with a well-designed feature extractor. As for the training procedure, the label refinement using forced alignment and the sequence training can yield significant gains on top of the frame-level cross-entropy criterion. Second, a deep convolutional neural network (DCNN) with automatically learned discriminative features demonstrates its superiority to DNN in the HMM framework. Moreover, to solve the challenging problem of distinguishing quite confusing classes due to the large vocabulary of Chinese characters, NN-based classifier should output 19900 HMM states as the classification units via a high-resolution modeling within each character. On the ICDAR 2013 competition task of CASIA-HWDB database, DNN-HMM yields a promising character error rate (CER) of 5.24% by making a good trade-off between the computational complexity and recognition accuracy. To the best of our knowledge, DCNN-HMM can achieve a best published CER of 3.53%.

中文翻译:

用于离线手写汉字识别的混合神经网络隐马尔可夫模型的综合研究

本文提出了一种使用混合神经网络隐马尔可夫模型(NN-HMM)的有效的无分段方法,用于离线手写中文文本识别(HCTR)。在一般的贝叶斯框架中,手写的中文文本行由HMM顺序建模,每个代表一个字符类,而采用基于NN的分类器来计算所有HMM状态的后验概率。对特征提取,字符建模和语言建模中的关键问题进行了全面研究,以显示NN-HMM框架对离线HCTR的有效性。首先,使用设计良好的特征提取器研究传统的深度神经网络(DNN)架构。至于训练程序 使用强制比对和序列训练进行的标签细化可以在帧级交叉熵准则的基础上产生显着的收益。其次,具有自动学习判别功能的深度卷积神经网络(DCNN)在HMM框架中展示了其优于DNN的优势。此外,为了解决由于汉字词汇量大而难以区分类的难题,基于NN的分类器应通过每个字符内的高分辨率建模输出190000 HMM状态作为分类单位。在CASIA-HWDB数据库的ICDAR 2013竞赛任务中,DNN-HMM通过在计算复杂度和识别精度之间进行权衡取舍,产生了有希望的5.24%的字符错误率(CER)。据我们所知,
更新日期:2018-06-15
down
wechat
bug