{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:08:08Z","timestamp":1758121688091,"version":"3.44.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20162-6","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T13:05:52Z","timestamp":1726751152000},"page":"27311-27325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Template-based text field segmentation for ID documents using dynamic squeezeboxes packing"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8598-0194","authenticated-orcid":false,"given":"Michael","family":"Zingerenko","sequence":"first","affiliation":[]},{"given":"Elena","family":"Limonova","sequence":"additional","affiliation":[]},{"given":"Vladimir V.","family":"Arlazarov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,18]]},"reference":[{"key":"20162_CR1","doi-asserted-by":"publisher","first-page":"72894","DOI":"10.1109\/ACCESS.2021.3072900","volume":"9","author":"D Baviskar","year":"2021","unstructured":"Baviskar D, Ahirrao S, Potdar V, Kotecha K (2021) Efficient automated processing of the unstructured documents using artificial intelligence: a systematic literature review and future directions. IEEE Access 9:72894\u201372936","journal-title":"IEEE Access"},{"issue":"1","key":"20162_CR2","first-page":"4","volume":"1","author":"A Khan","year":"2010","unstructured":"Khan A, Baharudin B, Lee LH, Khan K (2010) A review of machine learning algorithms for text-documents classification. J Adv Inf Technol 1(1):4\u201320","journal-title":"J Adv Inf Technol"},{"key":"20162_CR3","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.neucom.2021.04.114","volume":"453","author":"L Liu","year":"2021","unstructured":"Liu L, Wang Z, Qiu T, Chen Q, Lu Y, Suen CY (2021) Document image classification: progress over two decades. Neurocomputing 453:223\u2013240","journal-title":"Neurocomputing"},{"key":"20162_CR4","doi-asserted-by":"publisher","unstructured":"Arlazarov V, Andreeva EI, Bulatov K, Nikolaev D, Petrova O, Savelev BI, Slavin O (2022) Document image analysis and recognition: a survey. Comput Opt. https:\/\/doi.org\/10.18287\/2412-6179-co-1020","DOI":"10.18287\/2412-6179-co-1020"},{"key":"20162_CR5","doi-asserted-by":"crossref","unstructured":"Povolotskiy MA, Tropin DV (2019) Dynamic programming approach to template-based ocr. In: Eleventh international conference on machine vision (ICMV 2018), vol 11041. SPIE, pp 485\u2013492","DOI":"10.1117\/12.2522974"},{"key":"20162_CR6","doi-asserted-by":"crossref","unstructured":"Bulatov K, Matalov D, Arlazarov VV (2020) Midv-2019: challenges of the modern mobile-based document ocr. In: Twelfth International Conference on Machine Vision (ICMV 2019), vol 11433. SPIE, pp 717\u2013722","DOI":"10.1117\/12.2558438"},{"key":"20162_CR7","doi-asserted-by":"publisher","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017) East: an efficient and accurate scene text detector, pp 2642\u20132651. https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"},{"key":"20162_CR8","doi-asserted-by":"publisher","unstructured":"Baek Y, Lee B, Han D, Yun S, Lee, H (2019) Character region awareness for text detection. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 9357\u20139366. https:\/\/doi.org\/10.1109\/CVPR.2019.00959","DOI":"10.1109\/CVPR.2019.00959"},{"key":"20162_CR9","unstructured":"Xu Y, Xu Y, Lv T, Cui L, Wei F, Wang G, Lu Y, Flor\u00eancio DAF, Zhang C, Che W, Zhang M, Zhou L (2020) Layoutlmv2: multi-modal pre-training for visually-rich document understanding. CoRR. abs\/2012.14740 2012.14740"},{"key":"20162_CR10","doi-asserted-by":"publisher","unstructured":"Hirata NST, Barbera J, Terada R (2000) Text segmentation by automatically designed morphological operators. In: Proceedings 13th Brazilian symposium on computer graphics and image processing (Cat. No.PR00878), pp 284\u2013291. https:\/\/doi.org\/10.1109\/SIBGRA.2000.883924","DOI":"10.1109\/SIBGRA.2000.883924"},{"key":"20162_CR11","unstructured":"Slugin DG, Arlazarov VV (2017) Text fields extraction based on image processing. Trudy ISA RAN (Proceedings of ISA RAS). 67(4):65\u201373. FRC CSC RAS"},{"key":"20162_CR12","doi-asserted-by":"publisher","unstructured":"Ibrahim Z, Isa D, Rajkumar R (2008) Text and non-text segmentation and classification from document images. In: 2008 International conference on computer science and software engineering, vol 1, pp 973\u2013976. https:\/\/doi.org\/10.1109\/CSSE.2008.1516","DOI":"10.1109\/CSSE.2008.1516"},{"key":"20162_CR13","doi-asserted-by":"publisher","unstructured":"Rusi\u00f1ol M, Benkhelfallah T, dAndecy VP (2013) Field extraction from administrative documents by incremental structural templates. In: 2013 12th International conference on document analysis and recognition, pp 1100\u20131104. https:\/\/doi.org\/10.1109\/ICDAR.2013.223","DOI":"10.1109\/ICDAR.2013.223"},{"key":"20162_CR14","doi-asserted-by":"publisher","first-page":"28392","DOI":"10.1109\/ACCESS.2019.2901943","volume":"7","author":"Y Sun","year":"2019","unstructured":"Sun Y, Mao X, Hong S, Xu W, Gui G (2019) Template matching-based method for intelligent invoice information identification. IEEE Access 7:28392\u201328401","journal-title":"IEEE Access"},{"issue":"4","key":"20162_CR15","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/TPAMI.2010.135","volume":"33","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Zabih R (2010) Dynamic programming and graph algorithms in computer vision. IEEE Trans Pattern Anal Mach Intell 33(4):721\u2013740","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20162_CR16","doi-asserted-by":"publisher","unstructured":"El\u00a0Bahi H, Zatni A (2019) Text recognition in document images obtained by a smartphone based on deep convolutional and recurrent neural network. Multimed Tools Appl 78. https:\/\/doi.org\/10.1007\/s11042-019-07855-z","DOI":"10.1007\/s11042-019-07855-z"},{"key":"20162_CR17","doi-asserted-by":"publisher","unstructured":"Andreeva E, Arlazarov V, Gayer A, Dorokhov E, Sheshkus A, Slavin O (2019) Document recognition method based on convolutional neural network invariant to 180 degree rotation angle. Journal of information technologies and computing systems (JITCS). https:\/\/doi.org\/10.14357\/20718632190408","DOI":"10.14357\/20718632190408"},{"key":"20162_CR18","doi-asserted-by":"publisher","unstructured":"Hao L, Gao L, Yi X, Tang Z (2016) A table detection method for pdf documents based on convolutional neural networks. In: 2016 12th IAPR Workshop on document analysis systems (DAS), pp 287\u2013292. https:\/\/doi.org\/10.1109\/DAS.2016.23","DOI":"10.1109\/DAS.2016.23"},{"key":"20162_CR19","doi-asserted-by":"crossref","unstructured":"Yang X, Yumer E, Asente P, Kraley M, Kifer D, Lee\u00a0Giles C (2017) Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5315\u20135324","DOI":"10.1109\/CVPR.2017.462"},{"key":"20162_CR20","doi-asserted-by":"crossref","unstructured":"Lample G, Ballesteros M, Subramanian S, Kawakami K, Dyer C (2016) Neural architectures for named entity recognition","DOI":"10.18653\/v1\/N16-1030"},{"key":"20162_CR21","doi-asserted-by":"crossref","unstructured":"Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. 1802.05365","DOI":"10.18653\/v1\/N18-1202"},{"key":"20162_CR22","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. 1810.04805"},{"issue":"1","key":"20162_CR23","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62\u201366","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"20162_CR24","doi-asserted-by":"publisher","unstructured":"Skoryukina N, Arlazarov VV, Nikolaev DP (2020) Fast method of id documents location and type identification for mobile and server application. In: ICDAR 2019, pp. 850\u2013857. The Institute of Electrical and Electronics Engineers (IEEE), Manhattan, New York, U.S. https:\/\/doi.org\/10.1109\/ICDAR.2019.00141","DOI":"10.1109\/ICDAR.2019.00141"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20162-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20162-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20162-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T22:15:26Z","timestamp":1757110526000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20162-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":24,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["20162"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20162-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,9,18]]},"assertion":[{"value":"16 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}