{"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/improving-patch-based-scene-text-script","title":"Improving patch-based scene text script identification with ensembles of conjoined networks","arxiv_id":"1602.07480","date":"2016-02-24","proceeding":null,"authors":["Lluis Gomez","Anguelos Nicolaou","Dimosthenis Karatzas"],"abstract":"This paper focuses on the problem of script identification in scene text\nimages. Facing this problem with state of the art CNN classifiers is not\nstraightforward, as they fail to address a key characteristic of scene text\ninstances: their extremely variable aspect ratio. Instead of resizing input\nimages to a fixed aspect ratio as in the typical use of holistic CNN\nclassifiers, we propose here a patch-based classification framework in order to\npreserve discriminative parts of the image that are characteristic of its\nclass. We describe a novel method based on the use of ensembles of conjoined\nnetworks to jointly learn discriminative stroke-parts representations and their\nrelative importance in a patch-based classification scheme. Our experiments\nwith this learning procedure demonstrate state-of-the-art results in two public\nscript identification datasets. In addition, we propose a new public benchmark\ndataset for the evaluation of multi-lingual scene text end-to-end reading\nsystems. Experiments done in this dataset demonstrate the key role of script\nidentification in a complete end-to-end system that combines our script\nidentification method with a previously published text detector and an\noff-the-shelf OCR engine.","url_abs":"http://arxiv.org/abs/1602.07480v2","url_pdf":"http://arxiv.org/pdf/1602.07480v2.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":"improving-patch-based-scene-text-script","repo_url":"https://github.com/lluisgomez/script_identification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1602.07480","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}