{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shopsign-a-diverse-scene-text-dataset-of","title":"ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views","arxiv_id":"1903.10412","date":"2019-03-25","proceeding":null,"authors":["Chongsheng Zhang","Guowen Peng","Yuefeng Tao","Feifei Fu","Wei Jiang","George Almpanidis","Ke Chen"],"abstract":"In this paper, we introduce the ShopSign dataset, which is a newly developed\nnatural scene text dataset of Chinese shop signs in street views. Although a\nfew scene text datasets are already publicly available (e.g. ICDAR2015,\nCOCO-Text), there are few images in these datasets that contain Chinese\ntexts/characters. Hence, we collect and annotate the ShopSign dataset to\nadvance research in Chinese scene text detection and recognition.\n  The new dataset has three distinctive characteristics: (1) large-scale: it\ncontains 25,362 Chinese shop sign images, with a total number of 196,010\ntext-lines. (2) diversity: the images in ShopSign were captured in different\nscenes, from downtown to developing regions, using more than 50 different\nmobile phones. (3) difficulty: the dataset is very sparse and imbalanced. It\nalso includes five categories of hard images (mirror, wooden, deformed, exposed\nand obscure). To illustrate the challenges in ShopSign, we run baseline\nexperiments using state-of-the-art scene text detection methods (including\nCTPN, TextBoxes++ and EAST), and cross-dataset validation to compare their\ncorresponding performance on the related datasets such as CTW, RCTW and ICPR\n2018 MTWI challenge dataset.\n  The sample images and detailed descriptions of our ShopSign dataset are\npublicly available at: https://github.com/chongshengzhang/shopsign.","url_abs":"http://arxiv.org/abs/1903.10412v1","url_pdf":"http://arxiv.org/pdf/1903.10412v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shopsign-a-diverse-scene-text-dataset-of","repo_url":"https://github.com/chongshengzhang/shopsign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"shopsign-a-diverse-scene-text-dataset-of","repo_url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/CTPN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[{"slug":"shopsign","name":"ShopSign","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10412","atlas_url":"https://app.syntology.ai/?focus=1903.10412","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}