中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Handwritten Chinese character recognition by joint classification and similarity ranking

文献类型:会议论文

作者Cheng Cheng1; Xu-Yao Zhang2; Xiao-Hu Shao1; Xiang-Dong Zhou1
出版日期2016
会议日期October 23-26
会议地点Shenzhen, China
关键词Hccr
英文摘要
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.
会议录International Conference on Frontiers in Handwriting Recognition (ICFHR)
源URL[http://ir.ia.ac.cn/handle/173211/12470]  
专题自动化研究所_模式识别国家重点实验室_模式分析与学习团队
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]. 见:. Shenzhen, China. October 23-26.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

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。