Components Regulated Generation of Handwritten Chinese Text-lines in arbitrary length
文献类型:会议论文
作者 | Shuo Li1,3; Xiyan Liu1,3; Gaofeng Meng1,2,3; Shiming Xiang1,3; Chunhong Pan1 |
出版日期 | 2022-08 |
会议日期 | 2022-8 |
会议地点 | Montreal, QC, Canada. |
英文摘要 | Generating readable images of handwritten Chinese text-lines is very challenging due to complicated topological structures in Chinese. To address this problem, we propose a components regulated model named HCT-GAN to generate the entire lines of Chinese handwriting from text-line labels. Specifically, HCT-GAN is designed as a CGAN-based architecture that additionally integrates a Chinese text encoder (CTE), a sequence recognition module(SRM), and a spatial perception module (SPM). Compared with the one-hot embedding, CTE learns the latent content representation by reusing the structure and component embedding shared among the Chinese characters. SRM provides sequence-level constraints to the generated images. SPM can adaptively constrain the spatial correlation between the generated components, which facilitates the modeling of characters with complicated topological structures. Benefiting from such artful modeling, our model suffices to generate images of handwritten Chinese text-lines in arbitrary length. Extensive experimental results demonstrate that our model achieves state-of-the-art performance in handwritten Chinese lines generation. |
源URL | [http://ir.ia.ac.cn/handle/173211/52198] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Gaofeng Meng |
作者单位 | 1.National Laboratory of Pattern Recognition , Institute of Auto Chinese Academy of Sciences 2.CAS Centre for Artificial Intelligence and Robotics, HK Institute of Science and Innovation 3.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Shuo Li,Xiyan Liu,Gaofeng Meng,et al. Components Regulated Generation of Handwritten Chinese Text-lines in arbitrary length[C]. 见:. Montreal, QC, Canada.. 2022-8. |
入库方式: OAI收割
来源:自动化研究所
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。