{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:23:44Z","timestamp":1779294224402,"version":"3.51.4"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002261","name":"\u0420\u043e\u0441\u0441\u0438\u0439\u0441\u043a\u0438\u0439 \u0424\u043e\u043d\u0434 \u0424\u0443\u043d\u0434\u0430\u043c\u0435\u043d\u0442\u0430\u043b\u044c\u043d\u044b\u0445 \u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u043d\u0438\u0439","doi-asserted-by":"publisher","award":["17-29-03170"],"award-info":[{"award-number":["17-29-03170"]}],"id":[{"id":"10.13039\/501100002261","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002261","name":"\u0420\u043e\u0441\u0441\u0438\u0439\u0441\u043a\u0438\u0439 \u0424\u043e\u043d\u0434 \u0424\u0443\u043d\u0434\u0430\u043c\u0435\u043d\u0442\u0430\u043b\u044c\u043d\u044b\u0445 \u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u043d\u0438\u0439","doi-asserted-by":"publisher","award":["17-29-03236"],"award-info":[{"award-number":["17-29-03236"]}],"id":[{"id":"10.13039\/501100002261","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2974051","type":"journal-article","created":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T21:15:42Z","timestamp":1581714942000},"page":"32587-32600","source":"Crossref","is-referenced-by-count":73,"title":["Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9520-3278","authenticated-orcid":false,"given":"Yulia S.","family":"Chernyshova","sequence":"first","affiliation":[{"name":"Federal Research Center “Computer Science and Control” of RAS, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8970-8747","authenticated-orcid":false,"given":"Alexander V.","family":"Sheshkus","sequence":"additional","affiliation":[{"name":"Federal Research Center “Computer Science and Control” of RAS, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3260-9104","authenticated-orcid":false,"given":"Vladimir V.","family":"Arlazarov","sequence":"additional","affiliation":[{"name":"Institute for Information Transmission Problems (Kharkevich Institute) RAS, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.12.005"},{"key":"ref72","author":"lecunn","year":"2019","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref71","first-page":"165","article-title":"Shortest path segmentation: A method for training a neural network to recognize character strings","author":"burges","year":"2003","journal-title":"Proc IJCNN Int Joint Conf Neural Netw"},{"key":"ref70","year":"2020","journal-title":"Google"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref77","article-title":"Batch-normalized maxout network in network","author":"chang","year":"2015","journal-title":"arXiv 1511 02583"},{"key":"ref74","first-page":"53","article-title":"Learning algorithms for classification: A comparison on handwritten digit recognition","author":"lecun","year":"1995","journal-title":"Proc ICNN"},{"key":"ref39","article-title":"Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree","author":"lee","year":"2015","journal-title":"arXiv 1509 08985"},{"key":"ref75","article-title":"APAC: Augmented pattern classification with neural networks","author":"sato","year":"2015","journal-title":"arXiv 1505 03229"},{"key":"ref38","article-title":"Stacked what-where auto-encoders","author":"zhao","year":"2015","journal-title":"arXiv 1506 02351"},{"key":"ref78","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7178-3"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1109\/ICDAR.2015.7333943","article-title":"ICDAR2015 competition on smartphone document capture and OCR (SmartDoc)","author":"burie","year":"2015","journal-title":"Proc 2015 13th Int Conf Document Anal Recognit (ICDAR)"},{"key":"ref31","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"2014","journal-title":"arXiv 1406 2227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2505377.2505394"},{"key":"ref37","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2015","journal-title":"arXiv 1511 07289"},{"key":"ref36","article-title":"Fractional max-pooling","author":"graham","year":"2015","journal-title":"arXiv 1412 6071"},{"key":"ref35","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume":"28","author":"wan","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn (ICML)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref60","year":"2018","journal-title":"Tesseract OCR"},{"key":"ref62","first-page":"735","article-title":"OCR as a service: An experimental evaluation of Google Docs OCR, Tesseract, ABBYY FineReader, and Transym","volume":"2016","author":"tafti","year":"2016","journal-title":"Proc ISVC"},{"key":"ref61","article-title":"Efficient and effective OCR engine training","author":"clausner","year":"0","journal-title":"Int J Document Anal Recognit"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2016.69"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"ref64","article-title":"Brno mobile OCR dataset","author":"ki\u0161\u0161","year":"2019","journal-title":"arXiv 1907 01307"},{"key":"ref27","article-title":"Accurate scene text recognition based on recurrent neural network","volume":"9003","author":"su","year":"2014","journal-title":"Computer Vision"},{"key":"ref65","article-title":"Efficient, lexicon-free OCR using deep learning","author":"namysl","year":"2019","journal-title":"CoRR"},{"key":"ref66","year":"2019","journal-title":"ABBYY FineReader"},{"key":"ref29","author":"smith","year":"2016","journal-title":"Tesseract Blends Old and New OCR Technology"},{"key":"ref67","year":"2020","journal-title":"International Civil Aviation Organization ICAO Doc 9303"},{"key":"ref68","year":"2020","journal-title":"Dataset for Paper Efficient and Effective OCR Engine Training"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1117\/12.2310119"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3161187"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2371574.2371612"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4151-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1117\/12.2309497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07855-z"},{"key":"ref23","article-title":"Word recognition in a segmentation-free approach to OCR","author":"chen","year":"2002","journal-title":"Proc of Int Conf Document Analysis Recognition (ICDAR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.22204\/2410-4639-2016-092-04-55-71"},{"key":"ref25","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","author":"shi","year":"2015","journal-title":"arXiv 1507 05717"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-017-1255-5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00140"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1117\/12.2522955"},{"key":"ref57","article-title":"Recognition of images of korean characters using embedded networks","author":"ilyuhin","year":"2019","journal-title":"arXiv 1911 04241"},{"key":"ref56","first-page":"173","article-title":"New criteria for neural network encoder learning in the string segmentation problem","volume":"33","author":"sheshkus","year":"2019","journal-title":"Sensory Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.2522969"},{"key":"ref54","first-page":"65","article-title":"Comparison of the classifying and similarity metric-based neural networks through the recognition of the filed","volume":"33","author":"chirvonaya","year":"2019","journal-title":"Sensory Syst"},{"key":"ref53","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"arXiv 1611 03530"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.102"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18287\/2412-6179-2019-43-5-818-824"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1117\/12.2523087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2795104"},{"key":"ref15","first-page":"128","article-title":"A new segmentation method for connected characters in CAPTCHA","author":"lu","year":"2015","journal-title":"Proc Int Conf Control Autom Inf Sci (ICCAIS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.34"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.06.017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.09.026"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-012-0082-z"},{"key":"ref80","year":"2020","journal-title":"PRImA Text Evaluation Tool"},{"key":"ref4","article-title":"Mobile phone camera-based video scanning of paper documents","volume":"8357","author":"luqman","year":"2013","journal-title":"Camera-Based Document Analysis and Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.102"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.347"},{"key":"ref5","first-page":"85","article-title":"An independent character recognizer for distantly acquired mobile phone text images","author":"mai","year":"2016","journal-title":"Proc Int Conf Adv Technol Commun (ATC)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.214"},{"key":"ref49","first-page":"288","article-title":"Ai benchmark: Running deep neural networks on Android smartphones","author":"ignatov","year":"2018","journal-title":"Proc ECCV"},{"key":"ref9","first-page":"45","article-title":"Selecting optimal strategy for combining per-frame character recognition results in video stream","author":"bulatov","year":"2017","journal-title":"J Inf Technol Comput Syst"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1023\/A:1019127721878","article-title":"A new deep learning-based handwritten character recognition system on mobile computing devices","author":"weng","year":"0","journal-title":"Mobile Netw Appl"},{"key":"ref45","article-title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","author":"hasanpour","year":"2018","journal-title":"arXiv 1608 06037"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00049"},{"key":"ref47","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc NIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342102"},{"key":"ref44","article-title":"Towards principled design of deep convolutional networks: Introducing SimpNet","author":"hasanpour","year":"2018","journal-title":"arXiv 1802 06205"},{"key":"ref43","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08999509.pdf?arnumber=8999509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T17:40:10Z","timestamp":1751391610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8999509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2974051","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}