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
ISSN0031-3203
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关键词Cascaded generator Conditional generative adversarial networks Document image binarization Image generation Historical document analysis
DOI10.1016/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
被引频次:33[WOS]   [WOS记录]     [WOS相关记录]
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
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
[Zhao, Jinyuan]的文章
[Shi, Cunzhao]的文章
[Jia, Fuxi]的文章
百度学术
百度学术中相似的文章
[Zhao, Jinyuan]的文章
[Shi, Cunzhao]的文章
[Jia, Fuxi]的文章
必应学术
必应学术中相似的文章
[Zhao, Jinyuan]的文章
[Shi, Cunzhao]的文章
[Jia, Fuxi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: pr.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。