Knowledge Commons of Institute of Automation,CAS
Handwritten Chinese Character Blind Inpainting with Conditional Generative Adversarial Nets | |
Zhao Zhong; Fei Yin; Xu-Yao Zhang; Cheng-Lin Liu | |
2017 | |
会议名称 | 4th IAPR Asian Conference on Pattern Recognition |
会议日期 | November 26-29 |
会议地点 | Nanjing, China |
摘要 | It is very common to use a regular grid like Tian-zi-ge or Mi-zi-ge to help writing in Chinese handwriting environment, especially in education and postal area. Although regular grid is helpful for writing, it is a disaster for recognition. This paper focuses on handwritten Chinese character blind inpainting with regular grid and spot. To solve this problem, we use the recently proposed conditional generative adversarial nets (GANs). Different from the traditional engineering based method like line detection or edge detection, conditional GANs learn a map between target and training data. The generator reconstructs character directly from the data and the discriminator guides the training process to make the generated character more realistic. In this paper, we can automatically remove regular grid in handwritten Chinese character and reconstruct the character's strokes correctly. Moreover, the evaluation on classification task achieved a near state-of-the-art performance on the simulation database and got a convincing result on real world regular grid handwritten Chinese character database. |
关键词 | Hccr |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20003 |
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 | Cheng-Lin Liu |
作者单位 | 中科院自动化所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhao Zhong,Fei Yin,Xu-Yao Zhang,et al. Handwritten Chinese Character Blind Inpainting with Conditional Generative Adversarial Nets[C],2017. |
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 | ||
ACPR2017-Handwritten(1458KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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