CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Unsupervised adaptation of neural networks for Chinese handwriting recognition
Hong-Ming Yang; Xu-Yao Zhang; Fei Yin; Zhenbo Luo; Cheng-Lin Liu
2016
Conference NameInternational Conference on Frontiers in Handwriting Recognition (ICFHR)
Source PublicationInternational Conference on Frontiers in Handwriting Recognition (ICFHR)
Conference DateOctober 23-26
Conference PlaceShenzhen, China
Abstract
Writer adaptation is an important topic in handwriting
recognition, which can further improve the performance
of writer-independent recognizer. In this paper, we
propose combining the neural network classifier with style
transfer mapping (STM) for unsupervised writer adaptation,
which only require writer-specific unlabeled data, and therefore
is more common and efficient compared to supervised
adaptation. We use some techniques like dropout, ReLU,
momentum, and deeply supervised strategy to improve the
performance of the neural network classifier. For a specific
writer in the test data, an adaptation layer is added to the
pre-trained neural network classifier. In adaptation process,
only the parameters in adaptation layer are updated while
other parameters of the neural network are kept unchanged.
To train the adaptation layer, we use the same technology
as STM learning but redefine the source point set, target
point set and the corresponding confidence. Experiments on
the online Chinese handwriting database CASIA-OLHWDB1.1
demonstrate that our method is very efficient and effective
in improving classification accuracy. The experimental results
also show that our proposed method outperforms the previous
proposed learning vector quantization (LVQ) and modified
quadratic discriminant function (MQDF) with STM methods
for writer adaptation.
KeywordAdaptation
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12469
Collection模式识别国家重点实验室_模式分析与学习
Corresponding AuthorCheng-Lin Liu
Affiliation中科院自动化所
Recommended Citation
GB/T 7714
Hong-Ming Yang,Xu-Yao Zhang,Fei Yin,et al. Unsupervised adaptation of neural networks for Chinese handwriting recognition[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
PID4396673.pdf(291KB)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
[Hong-Ming Yang]'s Articles
[Xu-Yao Zhang]'s Articles
[Fei Yin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hong-Ming Yang]'s Articles
[Xu-Yao Zhang]'s Articles
[Fei Yin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hong-Ming Yang]'s Articles
[Xu-Yao Zhang]'s Articles
[Fei Yin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PID4396673.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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