Document image binarization with cascaded generators of conditional generative adversarial networks | |
Zhao, Jinyuan1,2; Shi, Cunzhao1; Jia, Fuxi1; Wang, Yanna1; Xiao, Baihua1 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2019-12-01 | |
卷号 | 96期号:1页码:12 |
产权排序 | 1 |
摘要 | Binarization is often the first step in many document analysis tasks and plays a key role in the subsequent steps. In this paper, we formulate binarization as an image-to-image generation task and introduce the conditional generative adversarial networks (cGANs) to solve the core problem of multi-scale information combination in binarization task. Our generator consists of two stages: In the first stage, sub generator Cl learns to extract text pixels from an input image. Different scales of the input image are processed by G1 and corresponding binary images are generated. In the second stage, our sub-generator G2 learns a combination of results at different scales from the first stage and produces the final binary result. We conduct comprehensive experiments of the proposed method on nine public document image binarization datasets. Experimental results show that compared with many classical and state-of-the-art approaches, our method gains promising performance in the accuracy and robustness of binarization. (C) 2019 Elsevier Ltd. All rights reserved. |
关键词 | Cascaded generator Conditional generative adversarial networks Document image binarization Image generation Historical document analysis |
DOI | 10.1016/j.patcog.2019.106968 |
关键词[WOS] | COMPETITION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC005] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC004] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC003] ; National Natural Science Foundation of China (NSFC)[71621002] ; National Natural Science Foundation of China (NSFC)[71621002] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC003] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC004] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC005] |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000487569700014 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 文字识别与文档分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26682 |
专题 | 复杂系统管理与控制国家重点实验室_影像分析与机器视觉 |
通讯作者 | Shi, Cunzhao |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China |
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, Jinyuan,Shi, Cunzhao,Jia, Fuxi,et al. Document image binarization with cascaded generators of conditional generative adversarial networks[J]. PATTERN RECOGNITION,2019,96(1):12. |
APA | Zhao, Jinyuan,Shi, Cunzhao,Jia, Fuxi,Wang, Yanna,&Xiao, Baihua.(2019).Document image binarization with cascaded generators of conditional generative adversarial networks.PATTERN RECOGNITION,96(1),12. |
MLA | Zhao, Jinyuan,et al."Document image binarization with cascaded generators of conditional generative adversarial networks".PATTERN RECOGNITION 96.1(2019):12. |
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 | ||
pr.pdf(3892KB) | 期刊论文 | 作者接受稿 | 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