Handwritten Chinese character recognition by joint classification and similarity ranking
Cheng Cheng1; Xu-Yao Zhang2; Xiao-Hu Shao1; Xiang-Dong Zhou1
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
Deep convolutional neural networks (DCNN) have
recently achieved state-of-the-art performance on handwritten
Chinese character recognition (HCCR). However, most of DCNN
models employ the softmax activation function and minimize
cross-entropy loss, which may loss some inter-class information.
To cope with this problem, we demonstrate a small but consistent
advantage of using both classification and similarity ranking
signals as supervision. Specifically, the presented method learns a
DCNN model by maximizing the inter-class variations and minimizing
the intra-class variations, and simultaneously minimizing
the cross-entropy loss. In addition, we also review some loss
functions for similarity ranking and evaluate their performance.
Our experiments demonstrate that the presented method achieves
state-of-the-art accuracy on the well-known ICDAR 2013 offline
HCCR competition dataset.
关键词Hccr
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12470
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 Cheng
作者单位1.重庆绿色科学研究院
2.中科院自动化所
推荐引用方式
GB/T 7714
Cheng Cheng,Xu-Yao Zhang,Xiao-Hu Shao,et al. Handwritten Chinese character recognition by joint classification and similarity ranking[C],2016.
条目包含的文件
条目无相关文件。
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
[Cheng Cheng]的文章
[Xu-Yao Zhang]的文章
[Xiao-Hu Shao]的文章
百度学术
百度学术中相似的文章
[Cheng Cheng]的文章
[Xu-Yao Zhang]的文章
[Xiao-Hu Shao]的文章
必应学术
必应学术中相似的文章
[Cheng Cheng]的文章
[Xu-Yao Zhang]的文章
[Xiao-Hu Shao]的文章
相关权益政策
暂无数据
收藏/分享
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。