{"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/a-fine-grained-approach-to-scene-text-script","title":"A fine-grained approach to scene text script identification","arxiv_id":"1602.07475","date":"2016-02-24","proceeding":null,"authors":["Lluis Gomez","Dimosthenis Karatzas"],"abstract":"This paper focuses on the problem of script identification in unconstrained\nscenarios. Script identification is an important prerequisite to recognition,\nand an indispensable condition for automatic text understanding systems\ndesigned for multi-language environments. Although widely studied for document\nimages and handwritten documents, it remains an almost unexplored territory for\nscene text images.\n  We detail a novel method for script identification in natural images that\ncombines convolutional features and the Naive-Bayes Nearest Neighbor\nclassifier. The proposed framework efficiently exploits the discriminative\npower of small stroke-parts, in a fine-grained classification framework.\n  In addition, we propose a new public benchmark dataset for the evaluation of\njoint text detection and script identification in natural scenes. Experiments\ndone in this new dataset demonstrate that the proposed method yields state of\nthe art results, while it generalizes well to different datasets and variable\nnumber of scripts. The evidence provided shows that multi-lingual scene text\nrecognition in the wild is a viable proposition. Source code of the proposed\nmethod is made available online.","url_abs":"http://arxiv.org/abs/1602.07475v1","url_pdf":"http://arxiv.org/pdf/1602.07475v1.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":[],"tasks":[{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[],"datasets_introduced":[{"slug":"mle2e","name":"MLe2e","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.07475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}