Handwritten Chinese Text Recognition Using Separable Multi-Dimensional Recurrent Neural Network

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Handwritten Chinese Text Recognition Using Separable Multi-Dimensional Recurrent Neural Network
	Wu YC(吴一超)1,2 ; Yin F(殷飞)1 ; Chen Z(陈卓)1,2 ; Liu CL(刘成林)1,2
	2017
会议名称	2017 14th IAPR International Conference on Document Analysis and Recognition
会议日期	2017-11-13
会议地点	日本京都
摘要	The Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) has been demonstrated successful in handwritten text recognition of Western and Arabic scripts. It is totally segmentation free and can be trained directly from text line images. However, the application of LSTM-RNNs (including Multi-Dimensional LSTM-RNN (MDLSTM-RNN)) to Chinese text recognition has shown limited success, even when training them with large datasets and using pre-training on datasets of other languages. In this paper, we propose a handwritten Chinese text recognition method by using Separable MDLSTMRNN (SMDLSTM-RNN) modules, which extract contextual information in various directions, and consume much less computation efforts and resources compared with the traditional MDLSTMRNN. Experimental results on the ICDAR-2013 competition dataset show that the proposed method performs significantly better than the previous LSTM-based methods, and can compete with the state-of-the-art systems.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/19794
专题	多模态人工智能系统全国重点实验室_模式分析与学习
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences 2.University of Chinese Academy of Sciences
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wu YC,Yin F,Chen Z,et al. Handwritten Chinese Text Recognition Using Separable Multi-Dimensional Recurrent Neural Network[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
3586a079.pdf（287KB）	会议论文		开放获取	CC BY-NC-SA	浏览