Document image binarization with cascaded generators of conditional generative adversarial networks. (December 2019)

• Record Type: Journal Article
• Authors: Zhao, Jinyuan; Shi, Cunzhao; Jia, Fuxi; Wang, Yanna; Xiao, Baihua
• Is Part Of: Pattern recognition. Volume 96(2019:Dec.)
• Publication Date: 2019-12
• Subjects: Cascaded generator -- Conditional generative adversarial networks -- Document image binarization -- Image generation -- Historical document analysis; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.106968
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel binarization method for degraded document image is presented. We apply cGANs strategy on document image binarization and propose a proper framework for this task. We solve the core problem of multi-scale information combination using cascaded sub-generators. Extensive experiments on various datasets show that our method is robust and effective. Abstract: 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 G 1 learns to extract text pixels from an input image. Different scales of the input image are processed by G 1 and corresponding binary images are generated. In the second stage, our sub-generator G 2 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.