{"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/mask-textspotter-an-end-to-end-trainable","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","arxiv_id":"1807.02242","date":"2018-07-06","proceeding":"ECCV 2018 9","authors":["Pengyuan Lyu","Minghui Liao","Cong Yao","Wenhao Wu","Xiang Bai"],"abstract":"Recently, models based on deep neural networks have dominated the fields of\nscene text detection and recognition. In this paper, we investigate the problem\nof scene text spotting, which aims at simultaneous text detection and\nrecognition in natural images. An end-to-end trainable neural network model for\nscene text spotting is proposed. The proposed model, named as Mask TextSpotter,\nis inspired by the newly published work Mask R-CNN. Different from previous\nmethods that also accomplish text spotting with end-to-end trainable deep\nneural networks, Mask TextSpotter takes advantage of simple and smooth\nend-to-end learning procedure, in which precise text detection and recognition\nare acquired via semantic segmentation. Moreover, it is superior to previous\nmethods in handling text instances of irregular shapes, for example, curved\ntext. Experiments on ICDAR2013, ICDAR2015 and Total-Text demonstrate that the\nproposed method achieves state-of-the-art results in both scene text detection\nand end-to-end text recognition tasks.","url_abs":"http://arxiv.org/abs/1807.02242v2","url_pdf":"http://arxiv.org/pdf/1807.02242v2.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":"mask-textspotter-an-end-to-end-trainable","repo_url":"https://github.com/lvpengyuan/masktextspotter.caffe2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"Mask TextSpotter","rank_in_archive_order":3,"of":16,"metrics":{"F-Measure":"91.7%","Precision":"95","Recall":"88.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"Mask TextSpotter","rank_in_archive_order":21,"of":43,"metrics":{"F-Measure":"86","Precision":"91.6","Recall":"81"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset":"Total-Text","model":"Mask TextSpotter","rank_in_archive_order":25,"of":27,"metrics":{"F-Measure":"61.3%","Precision":"69","Recall":"55"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-inverse-text","task":"Text Spotting","dataset":"Inverse-Text","model":"MaskTextSpotter v2","rank_in_archive_order":5,"of":9,"metrics":{"F-measure (%) - Full Lexicon":"43.5","F-measure (%) - No Lexicon":"39.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}