Simultaneous Script Identification and Handwriting Recognition via Multi-Task Learning of Recurrent Neural Networks
Chen, Zhuo1,2; Wu, Yichao1,2; Yin, Fei1; Liu, Chenglin1,2
2017
会议名称International Conference on Document Analysis and Recognition
会议日期2017.11.9-15
会议地点Kyoto, Japan
摘要In this paper, we propose a method for simultaneous script identification and handwritten text line recognition in multi-task learning framework. Firstly, we use Separable Multi-Dimensional Long Short-Term Memory (SepMDLSTM) to encode the input text line images based on convolutional feature extraction. Then, the extracted features are fed into two classification modules for script identification and multi-script text recognition, respectively. All the network parameters are trained end-to-end by multi-task learning where the script identification task and the text recognition task are aimed to minimize the Negative Log Likelihood (NLL) loss and Connectionist Temporal Classification (CTC) loss, respectively. We evaluated the performance of the proposed method on handwritten text line datasets of three languages, namely, IAM (English), Rimes (French) and IFN/ENIT (Arabic). Experimental results demonstrate the multitask learning framework performs superiorly for both script identification and text recognition. Particularly, the accuracy of script identification is higher than 99.9% and the character error rate (CER) of text recognition is even lower than that of some single-script text recognition systems.
其他摘要该工作提出了一种在多任务学习框架(multi-task)中同时进行语种分类与文本识别的方法。
首先,我们使用卷积神经网络与可分离的MDLSTM对输入的文本行图像进行编码。然后提取出的特征分别输入到语种分类模块与多语种文本识别模块中。
网络的全部参数都是通过多任务学习进行端到端的更新,其中语种分类模块与文本识别模块的损失函数分别为负似然对数(NLL)与连接时序分类(CTC)。
在IAM(英语)、Rimes(法语)和IFN/ENIT(阿拉伯语)三个数据集进行实验,我们的网络的语种分类正确率为99.92%,字符集识别正确率分别为88.85,91.71,85.06。
关键词Multi-task Learning Sepmdlstm Script Identification Language Identification Handwritten Text Recognition
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20012
专题模式识别国家重点实验室_模式分析与学习
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Chen, Zhuo,Wu, Yichao,Yin, Fei,et al. Simultaneous Script Identification and Handwriting Recognition via Multi-Task Learning of Recurrent Neural Networks[C],2017.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ICDAR2017-Simultaneo(467KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chen, Zhuo]的文章
[Wu, Yichao]的文章
[Yin, Fei]的文章
百度学术
百度学术中相似的文章
[Chen, Zhuo]的文章
[Wu, Yichao]的文章
[Yin, Fei]的文章
必应学术
必应学术中相似的文章
[Chen, Zhuo]的文章
[Wu, Yichao]的文章
[Yin, Fei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ICDAR2017-Simultaneous Script Identification and Recognition via MTL of RNN-ChenZ.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。