Joint Training of Conditional Random Fields and Neural Networks for Stroke Classification in Online Handwritten Documents | |
Ye, Jun-Yu; Zhang, Yan-Ming; Liu, Cheng-Lin | |
2016 | |
会议日期 | Dec. 04-08, 2016 |
会议地点 | Cancun, Mexico |
关键词 | Crf |
英文摘要 |
The task of text/non-text stroke classification in online handwritten documents is an essential preprocessing step in document analysis. It is also a challenging problem since in many cases local features are not enough to generate high accuracy results and contextual information, such as temporal information and spatial information, must be carefully considered. In this paper, we propose a novel method, which jointly trains a combined model of conditional random fields and neural networks, to solve this problem. Both our unary and pairwise potentials are formulated as neural networks. The parameters of conditional random fields and neural networks are learned together during the training process. With much fewer parameters and faster speed, our method achieves impressive performance on the IAMonDo database, a publicly available database of freely handwritten documents. |
会议录 | 23rd International Conference on Pattern Recognition |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/12263] |
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 | Zhang, Yan-Ming |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Ye, Jun-Yu,Zhang, Yan-Ming,Liu, Cheng-Lin. Joint Training of Conditional Random Fields and Neural Networks for Stroke Classification in Online Handwritten Documents[C]. 见:. Cancun, Mexico. Dec. 04-08, 2016. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论