Document image binarization with cascaded generators of conditional generative adversarial networks

doi:10.1016/j.patcog.2019.106968

	Document image binarization with cascaded generators of conditional generative adversarial networks
	Zhao, Jinyuan 1,2; Shi, Cunzhao1 ; Jia, Fuxi1 ; Wang, Yanna1 ; Xiao, Baihua1
刊名	PATTERN RECOGNITION
	2019-12-01
卷号	96 页码:12
关键词	Cascaded generator Conditional generative adversarial networks Document image binarization Image generation Historical document analysis
ISSN号	0031-3203
DOI	10.1016/j.patcog.2019.106968
通讯作者	Shi, Cunzhao(cunzhao.shi@ia.ac.cn)
英文摘要	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.
资助项目	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关键词	COMPETITION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000487569700014
资助机构	National Natural Science Foundation of China (NSFC) ; Key Programs of the Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/26681]
专题	中国科学院自动化研究所
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
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,2019,96:12.
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,96,12.
MLA	Zhao, Jinyuan,et al."Document image binarization with cascaded generators of conditional generative adversarial networks".PATTERN RECOGNITION 96(2019):12.