{"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/stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","arxiv_id":"1707.08831","date":"2017-07-27","proceeding":null,"authors":["Christian Bartz","Haojin Yang","Christoph Meinel"],"abstract":"Detecting and recognizing text in natural scene images is a challenging, yet\nnot completely solved task. In re- cent years several new systems that try to\nsolve at least one of the two sub-tasks (text detection and text recognition)\nhave been proposed. In this paper we present STN-OCR, a step towards\nsemi-supervised neural networks for scene text recognition, that can be\noptimized end-to-end. In contrast to most existing works that consist of\nmultiple deep neural networks and several pre-processing steps we propose to\nuse a single deep neural network that learns to detect and recognize text from\nnatural images in a semi-supervised way. STN-OCR is a network that integrates\nand jointly learns a spatial transformer network, that can learn to detect text\nregions in an image, and a text recognition network that takes the identified\ntext regions and recognizes their textual content. We investigate how our model\nbehaves on a range of different tasks (detection and recognition of characters,\nand lines of text). Experimental results on public benchmark datasets show the\nability of our model to handle a variety of different tasks, without\nsubstantial changes in its overall network structure.","url_abs":"http://arxiv.org/abs/1707.08831v1","url_pdf":"http://arxiv.org/pdf/1707.08831v1.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":"stn-ocr-a-single-neural-network-for-text","repo_url":"https://github.com/Bartzi/stn-ocr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":null},{"paper_slug":"stn-ocr-a-single-neural-network-for-text","repo_url":"https://github.com/Narp99/FRI_2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"stn-ocr-a-single-neural-network-for-text","repo_url":"https://github.com/pokalaanirudh/Text-spotting-in-wild-using-YOLO.","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"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"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"STN-OCR","rank_in_archive_order":5,"of":16,"metrics":{"F-Measure":"90.3%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}