Knowledge Commons of Institute of Automation,CAS
Fully Convolutional Network Based Skeletonization for Handwritten Chinese Characters | |
Wang TQ(王铁强)1,2![]() ![]() | |
2018 | |
会议名称 | The 32nd AAAI Conference on Artificial Intelligence |
会议日期 | 2018-2 |
会议地点 | 美国,新奥尔良 |
摘要 | Structural analysis of handwritten characters relies heavily on robust skeletonization of strokes, which has not been solved well by previous thinning methods. This paper presents an effective fully convolutional network (FCN) to extract stroke skeletons for handwritten Chinese characters. We combine the holistically-nested architecture with regressive dense upsampling convolution (rDUC) and recently proposed hybrid dilated convolution (HDC) to generate pixel-level prediction for skeleton extraction. We evaluate our method on character images synthesized from the online handwritten dataset CASIA-OLHWDB and achieve higher accuracy of skeleton pixel detection than traditional thinning algorithms. We also conduct skeleton based character recognition experiments using convolutional neural network (CNN) classifiers on offline/online handwritten datasets, and obtained comparable accuracies with recognition on original character images. This implies the skeletonization loses little shape information. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44413 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Liu CL(刘成林) |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence of Brain Science and Intelligence Technology |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang TQ,Liu CL. Fully Convolutional Network Based Skeletonization for Handwritten Chinese Characters[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
AAAI18-Wang-Liu.pdf(1764KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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 |
[Wang TQ(王铁强)]的文章 |
[Liu CL(刘成林)]的文章 |
百度学术 |
百度学术中相似的文章 |
[Wang TQ(王铁强)]的文章 |
[Liu CL(刘成林)]的文章 |
必应学术 |
必应学术中相似的文章 |
[Wang TQ(王铁强)]的文章 |
[Liu CL(刘成林)]的文章 |
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