{"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/textboxes-a-single-shot-oriented-scene-text","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","arxiv_id":"1801.02765","date":"2018-01-09","proceeding":null,"authors":["Minghui Liao","Baoguang Shi","Xiang Bai"],"abstract":"Scene text detection is an important step of scene text recognition system\nand also a challenging problem. Different from general object detection, the\nmain challenges of scene text detection lie on arbitrary orientations, small\nsizes, and significantly variant aspect ratios of text in natural images. In\nthis paper, we present an end-to-end trainable fast scene text detector, named\nTextBoxes++, which detects arbitrary-oriented scene text with both high\naccuracy and efficiency in a single network forward pass. No post-processing\nother than an efficient non-maximum suppression is involved. We have evaluated\nthe proposed TextBoxes++ on four public datasets. In all experiments,\nTextBoxes++ outperforms competing methods in terms of text localization\naccuracy and runtime. More specifically, TextBoxes++ achieves an f-measure of\n0.817 at 11.6fps for 1024*1024 ICDAR 2015 Incidental text images, and an\nf-measure of 0.5591 at 19.8fps for 768*768 COCO-Text images. Furthermore,\ncombined with a text recognizer, TextBoxes++ significantly outperforms the\nstate-of-the-art approaches for word spotting and end-to-end text recognition\ntasks on popular benchmarks. Code is available at:\nhttps://github.com/MhLiao/TextBoxes_plusplus","url_abs":"http://arxiv.org/abs/1801.02765v3","url_pdf":"http://arxiv.org/pdf/1801.02765v3.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":"textboxes-a-single-shot-oriented-scene-text","repo_url":"https://github.com/MhLiao/TextBoxes_plusplus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"textboxes-a-single-shot-oriented-scene-text","repo_url":"https://github.com/jercas/TextBoxes_plusplus_tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"textboxes-a-single-shot-oriented-scene-text","repo_url":"https://github.com/sonamghosh/local_hack_day_2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-coco-text","task":"Scene Text Detection","dataset":"COCO-Text","model":"TextBoxes++_MS","rank_in_archive_order":2,"of":6,"metrics":{"F-Measure":"58.72","Precision":"60.87","Recall":"56.7"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"TextBoxes++_MS","rank_in_archive_order":8,"of":16,"metrics":{"F-Measure":"88%%","Precision":"91","Recall":"84"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"Quad_MS","rank_in_archive_order":31,"of":43,"metrics":{"F-Measure":"82.9","Precision":"87.8","Recall":"78.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.02765","atlas_url":"https://app.syntology.ai/?focus=1801.02765","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}