Unsupervised adaptation of neural networks for Chinese handwriting recognition
Hong-Ming Yang; Xu-Yao Zhang; Fei Yin; Zhenbo Luo; Cheng-Lin Liu
2016
会议名称International Conference on Frontiers in Handwriting Recognition (ICFHR)
会议录名称International Conference on Frontiers in Handwriting Recognition (ICFHR)
会议日期October 23-26
会议地点Shenzhen, China
摘要
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.
关键词Adaptation
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12469
专题模式识别国家重点实验室_模式分析与学习
通讯作者Cheng-Lin Liu
作者单位中科院自动化所
推荐引用方式
GB/T 7714
Hong-Ming Yang,Xu-Yao Zhang,Fei Yin,et al. Unsupervised adaptation of neural networks for Chinese handwriting recognition[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
PID4396673.pdf(291KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[Hong-Ming Yang]的文章
[Xu-Yao Zhang]的文章
[Fei Yin]的文章
百度学术
百度学术中相似的文章
[Hong-Ming Yang]的文章
[Xu-Yao Zhang]的文章
[Fei Yin]的文章
必应学术
必应学术中相似的文章
[Hong-Ming Yang]的文章
[Xu-Yao Zhang]的文章
[Fei Yin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: PID4396673.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。