CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Evaluation of Neural Network Language Models in Handwritten Chinese Text Recognition
Wu YC(吴一超); Yin F(殷飞); Liu CL(刘成林)
2015
Conference Name2015 13th International Conference on Document Analysis and Recognition
Conference Date2015-8-23
Conference Place法国南锡
AbstractHandwritten Chinese text recognition based on
over-segmentation and path search integrating contexts has been
demonstrated successful, where language models play an important
role. Recently, neural network language models (NNLMs)
have shown superiority to back-off N-gram language models
(BLMs) in handwriting recognition, but have not been studied
in Chinese text recognition system. This paper investigates the
effects of NNLMs in handwritten Chinese text recognition and
compares the performance with BLMs. We trained characterlevel
language models in 3-, 4- and 5- gram on large scale corpora
and applied them in text line recognition system. Experimental
results on the CASIA-HWDB database show that NNLM and
BLM of the same order perform comparably, and the hybrid
model by interpolating NNLM and BLM improves the recognition
performance significantly.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19797
Collection模式识别国家重点实验室_模式分析与学习
AffiliationInstitute of Institute of Automation,Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wu YC,Yin F,Liu CL. Evaluation of Neural Network Language Models in Handwritten Chinese Text Recognition[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
paper_078.pdf(1450KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wu YC(吴一超)]'s Articles
[Yin F(殷飞)]'s Articles
[Liu CL(刘成林)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu YC(吴一超)]'s Articles
[Yin F(殷飞)]'s Articles
[Liu CL(刘成林)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu YC(吴一超)]'s Articles
[Yin F(殷飞)]'s Articles
[Liu CL(刘成林)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: paper_078.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.