{"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/aster-an-attentional-scene-text-recognizer","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","arxiv_id":null,"date":"2018-06-25","proceeding":"good 2018 6","authors":["Baoguang Shi","Mingkun Yang","Xinggang Wang","Pengyuan Lyu","Cong Yao","and Xiang Bai"],"abstract":"SCENE text recognition has attracted great interest from\r\nthe academia and the industry in recent years owing to\r\nits importance in a wide range of applications. Despite the\r\nmaturity of Optical Character Recognition (OCR) systems\r\ndedicated to document text, scene text recognition remains\r\na challenging problem. The large variations in background,\r\nappearance, and layout pose significant challenges, which\r\nthe traditional OCR methods cannot handle effectively.\r\nRecent advances in scene text recognition are driven\r\nby the success of deep learning-based recognition models.\r\nAmong them are methods that recognize text by characters\r\nusing convolutional neural networks (CNN), methods that\r\nclassify words with CNNs [24], [26], and methods that\r\nrecognize character sequences using a combination of a\r\nCNN and a recurrent neural network (RNN) [54]. In spite\r\nof their success, these methods do not explicitly address the\r\nproblem of irregular text, which is text that is not horizontal\r\nand frontal, has curved layout, etc. Instances of irregular\r\ntext frequently appear in natural scenes. As exemplified\r\nin Figure 1, typical cases include oriented text, perspective\r\ntext [49], and curved text. Designed without the invariance\r\nto such irregularities, previous methods often struggle in\r\nrecognizing such text instances.","url_abs":"http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.pdf","url_pdf":"http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.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":"aster-an-attentional-scene-text-recognizer","repo_url":"https://github.com/Media-Smart/vedastr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"aster-an-attentional-scene-text-recognizer","repo_url":"https://github.com/ayumiymk/aster.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"aster-an-attentional-scene-text-recognizer","repo_url":"https://github.com/bgshih/aster","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"aster-an-attentional-scene-text-recognizer","repo_url":"https://github.com/topdu/openocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"ASTER","rank_in_archive_order":32,"of":38,"metrics":{"Accuracy":"91.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"ASTER","rank_in_archive_order":22,"of":27,"metrics":{"Accuracy":"76.1"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"ASTER","rank_in_archive_order":27,"of":37,"metrics":{"Accuracy":"89.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}