{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:27:20Z","timestamp":1780763240228,"version":"3.54.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004077","name":"Kocaeli \u00dcniversitesi","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004077","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s10489-022-04306-5","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T08:02:50Z","timestamp":1668499370000},"page":"15295-15310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["A document image classification system fusing deep and machine learning models"],"prefix":"10.1007","volume":"53","author":[{"given":"Sevin\u00e7 \u0130lhan","family":"Omurca","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0658-592X","authenticated-orcid":false,"given":"Ekin","family":"Ekinci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Semih","family":"Sevim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eren Berk","family":"Edin\u00e7","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S\u00fcleyman","family":"Eken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"Sayar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,15]]},"reference":[{"key":"4306_CR1","doi-asserted-by":"crossref","unstructured":"Mahajan K, Sharma M, Vig L (2019) Character keypoint-based homography estimation in scanned documents for efficient information extraction. In: 2019 international conference on document analysis and recognition workshops (ICDARW), vol 4. IEEE, pp 25\u201330","DOI":"10.1109\/ICDARW.2019.30060"},{"key":"4306_CR2","doi-asserted-by":"crossref","unstructured":"Menhour H et al (2021) Searchable Turkish OCRed historical newspaper collection 1928\u20131942. In: Journal of information science. SAGE Publications Sage UK, London, England, p 01655515211000642","DOI":"10.1177\/01655515211000642"},{"key":"4306_CR3","doi-asserted-by":"publisher","first-page":"97996","DOI":"10.1109\/ACCESS.2019.2930339","volume":"7","author":"S Eken","year":"2019","unstructured":"Eken S, Menhour H, K\u00fcksal K (2019) DoCA: a content-based automatic classification system over digital documents. IEEE Access 7:97996\u201398004","journal-title":"IEEE Access"},{"issue":"1","key":"4306_CR4","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1177\/0165551511429418","volume":"38","author":"T Blanke","year":"2012","unstructured":"Blanke T, Bryant M, Hedges M (2012) Ocropodium: open source OCR for small-scale historical archives. J Inf Sci 38(1):76\u201386","journal-title":"J Inf Sci"},{"key":"4306_CR5","doi-asserted-by":"crossref","unstructured":"Hua Y et al (2020) Attention-based graph neural network with global context awareness for document understanding. In: China national conference on Chinese computational linguistics, Springer, pp 45\u201356","DOI":"10.1007\/978-3-030-63031-7_4"},{"key":"4306_CR6","doi-asserted-by":"crossref","unstructured":"Xu Y et al (2020) Layoutlm: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & Data Mining, pp 1192\u20131200","DOI":"10.1145\/3394486.3403172"},{"issue":"3","key":"4306_CR7","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s10032-021-00383-3","volume":"24","author":"M Mathew","year":"2021","unstructured":"Mathew M et al (2021) Asking questions on handwritten document collections. Int J Doc Anal Recog (IJDAR) 24(3):235\u2013249","journal-title":"Int J Doc Anal Recog (IJDAR)"},{"issue":"4","key":"4306_CR8","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s10032-021-00382-4","volume":"24","author":"R Elanwar","year":"2021","unstructured":"Elanwar R et al (2021) Extracting text from scanned Arabic books: a large-scale benchmark dataset and a fine-tuned Faster-R-CNN model. Int J Doc Anal Recog (IJDAR) 24(4):349\u2013362","journal-title":"Int J Doc Anal Recog (IJDAR)"},{"key":"4306_CR9","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 et al (2021) Document image classification: progress over two decades. Neurocomputing 453:223\u2013240","journal-title":"Neurocomputing"},{"key":"4306_CR10","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.patrec.2021.11.010","volume":"155","author":"AC Rouhou","year":"2022","unstructured":"Rouhou AC et al (2022) Transformer-based approach for joint handwriting and named entity recognition in historical document. Pattern Recog Lett 155:128\u2013134","journal-title":"Pattern Recog Lett"},{"key":"4306_CR11","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patrec.2013.10.030","volume":"43","author":"J Kumar","year":"2014","unstructured":"Kumar J, Ye P, Doermann D (2014) Structural similarity for document image classification and retrieval. Pattern Recog Lett 43:119\u2013126","journal-title":"Pattern Recog Lett"},{"key":"4306_CR12","doi-asserted-by":"crossref","unstructured":"Kang L et al (2014) Convolutional neural networks for document image classification. In: 2014 22nd international conference on pattern recognition, IEEE, pp \u20133172","DOI":"10.1109\/ICPR.2014.546"},{"key":"4306_CR13","doi-asserted-by":"crossref","unstructured":"Afzal MZ et al (2015) Deepdocclassifier: document classification with deep convolutional neural network. In: 2015 13th international conference on document analysis and recognition (ICDAR), IEEE, pp 1111\u20131115","DOI":"10.1109\/ICDAR.2015.7333933"},{"key":"4306_CR14","doi-asserted-by":"crossref","unstructured":"Harley AW, Ufkes A, Derpanis KG (2015) Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th international conference on document analysis and recognition (ICDAR), IEEE, pp 991\u2013995","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"4306_CR15","doi-asserted-by":"crossref","unstructured":"Roy S, Das A, Bhattacharya U (2016) Generalized stacking of layerwise-trained deep convolutional neural networks for document image classification. In: 2016 23rd international conference on pattern recognition (ICPR), IEEE, pp 1273\u20131278","DOI":"10.1109\/ICPR.2016.7899812"},{"key":"4306_CR16","doi-asserted-by":"crossref","unstructured":"Csurka G (2017) Document image classification, with a specific view on applications of patent images. In: Current challenges in patent information retrieval, Springer, pp 325\u2013350","DOI":"10.1007\/978-3-662-53817-3_12"},{"key":"4306_CR17","doi-asserted-by":"crossref","unstructured":"Tensmeyer C, Martinez T (2017) Analysis of convolutional neural networks for document image classification. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 388\u2013393","DOI":"10.1109\/ICDAR.2017.71"},{"key":"4306_CR18","doi-asserted-by":"crossref","unstructured":"Yaman D, Eyiokur FI, Ekenel HK (2017) Comparison of convolutional neural network models for document image classification. In: 2017 25th signal processing and communications applications conference (SIU), IEEE, pp 1\u20134","DOI":"10.1109\/SIU.2017.7960562"},{"key":"4306_CR19","doi-asserted-by":"crossref","unstructured":"Afzal MZ et al (2017) Cutting the error by half: investigation of very deep cnn and advanced training strategies for document image classification. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 883\u2013888","DOI":"10.1109\/ICDAR.2017.149"},{"issue":"2","key":"4306_CR20","doi-asserted-by":"publisher","first-page":"78","DOI":"10.2352\/ISSN.2470-1173.2017.2.VIPC-412","volume":"2017","author":"S Zavalishin","year":"2017","unstructured":"Zavalishin S et al (2017) Document image classification on the basis of layout information. Electr Imaging 2017(2):78\u201386","journal-title":"Electr Imaging"},{"key":"4306_CR21","doi-asserted-by":"crossref","unstructured":"K\u00f6lsch A et al (2017) Real-time document image classification using deep CNN and extreme learning machines. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 1318\u20131323","DOI":"10.1109\/ICDAR.2017.217"},{"key":"4306_CR22","doi-asserted-by":"crossref","unstructured":"Das A et al (2018) Document image classification with intra-domain transfer learning and stacked generalization of deep convolutional neural networks. In: 2018 24th international conference on pattern recognition (ICPR), IEEE, pp 3180\u20133185","DOI":"10.1109\/ICPR.2018.8545630"},{"key":"4306_CR23","doi-asserted-by":"crossref","unstructured":"Hassanpour M, Malek H (2019) Document Image Classification using SqueezeNet Convolutional Neural Network. In: 2019 5th Iranian conference on signal processing and intelligent systems (ICSPIS), IEEE, pp 1\u20134","DOI":"10.1109\/ICSPIS48872.2019.9066032"},{"key":"4306_CR24","doi-asserted-by":"crossref","unstructured":"Mohsenzadegan K et al (2020) A convolutional neural network model for robust classification of document-images under real-world hard conditions. In: Developments of artificial intelligence technologies in computation and robotics: proceedings of the 14th international FLINS conference (FLINS 2020), World Scientific, pp 1023\u20131030","DOI":"10.1142\/9789811223334_0123"},{"key":"4306_CR25","doi-asserted-by":"publisher","first-page":"164358","DOI":"10.1109\/ACCESS.2021.3133200","volume":"9","author":"SA Siddiqui","year":"2021","unstructured":"Siddiqui SA, Dengel A, Ahmed S (2021) Self-supervised representation learning for document image classification. IEEE Access 9:164358\u2013164367","journal-title":"IEEE Access"},{"issue":"4","key":"4306_CR26","doi-asserted-by":"publisher","first-page":"043024","DOI":"10.1117\/1.JEI.30.4.043024","volume":"30","author":"Y Liu","year":"2021","unstructured":"Liu Y, Soh L-K, Lorang E (2021) Investigating coupling preprocessing with shallow and deep convolutional neural networks in document image classification. J Electron Imaging 30(4):043024","journal-title":"J Electron Imaging"},{"key":"4306_CR27","unstructured":"\u015eahin S et al (2020) Dijital Dok\u00fcmanlar\u0131n Anahtar Kelime Tabanl\u0131 Do\u011frulanmas\u0131. In: Proceedings of the 6. Ulusal Y\u00fcksek Ba\u015far\u0131ml\u0131 Hesaplama Konferans\u0131 (in Turkish), pp 1\u20136"},{"key":"4306_CR28","doi-asserted-by":"crossref","unstructured":"Noce L et al (2016) Embedded textual content for document image classification with convolutional neural networks. In: Proceedings of the 2016 ACM symposium on document engineering, pp 165\u2013173","DOI":"10.1145\/2960811.2960814"},{"key":"4306_CR29","doi-asserted-by":"crossref","unstructured":"Audebert N et al (2019) Multimodal deep networks for text and image-based document classification. In: Joint european conference on machine learning and knowledge discovery in databases, Springer, pp 427\u2013443","DOI":"10.1007\/978-3-030-43823-4_35"},{"key":"4306_CR30","doi-asserted-by":"crossref","unstructured":"Jain R, Wigington C (2019) Multimodal Document Image Classification. In: 2019 international conference on document analysis and recognition (ICDAR), IEEE, pp 71\u201377","DOI":"10.1109\/ICDAR.2019.00021"},{"key":"4306_CR31","doi-asserted-by":"crossref","unstructured":"Asim MN et al (2019) Two stream deep network for document image classification. In: 2019 international conference on document analysis and recognition (ICDAR), IEEE, pp 1410\u20131416","DOI":"10.1109\/ICDAR.2019.00227"},{"key":"4306_CR32","doi-asserted-by":"crossref","unstructured":"Bakkali S et al (2020) Cross-modal deep networks for document image classification. In: 2020 ieee international conference on image processing (ICIP), IEEE, pp 2556\u20132560","DOI":"10.1109\/ICIP40778.2020.9191268"},{"key":"4306_CR33","doi-asserted-by":"crossref","unstructured":"Ferrando J et al (2020) Improving accuracy and speeding up Document Image Classification through parallel systems. In: International conference on computational science, Springer, pp 387\u2013400","DOI":"10.1007\/978-3-030-50417-5_29"},{"key":"4306_CR34","doi-asserted-by":"crossref","unstructured":"Cosma A et al (2020) Self-supervised Representation Learning on Document Images. In: International workshop on document analysis systems, Springer, pp 103\u2013117","DOI":"10.1007\/978-3-030-57058-3_8"},{"key":"4306_CR35","doi-asserted-by":"crossref","unstructured":"Bakkali S et al (2020) Visual and textual deep feature fusion for document image classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 562\u2013563","DOI":"10.1109\/CVPRW50498.2020.00289"},{"key":"4306_CR36","doi-asserted-by":"publisher","first-page":"104302","DOI":"10.1016\/j.ijmedinf.2020.104302","volume":"144","author":"H Goodrum","year":"2020","unstructured":"Goodrum H, Roberts K, Bernstam EV (2020) Automatic classification of scanned electronic health record documents. Int J Med Inf 144:104302","journal-title":"Int J Med Inf"},{"key":"4306_CR37","doi-asserted-by":"crossref","unstructured":"Bakkali S et al (2021) EAML: ensemble self-attention-based mutual learning network for document image classification. Int J Doc Anal Recog (IJDAR) 24(3):251\u2013268","DOI":"10.1007\/s10032-021-00378-0"},{"key":"4306_CR38","doi-asserted-by":"crossref","unstructured":"Prieto JR et al (2021) Textual-content-based classification of bundles of untranscribed manuscript images","DOI":"10.1109\/ICPR48806.2021.9412688"},{"issue":"159","key":"4306_CR39","first-page":"2","volume":"2007","author":"A Kay","year":"2007","unstructured":"Kay A (2007) Tesseract: an open-source optical character recognition engine. Linux J 2007(159):2","journal-title":"Linux J"},{"issue":"9","key":"4306_CR40","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.1109\/TKDE.2016.2563436","volume":"28","author":"B Tang","year":"2016","unstructured":"Tang B, Kay S, He H (2016) Toward optimal feature selection in naive Bayes for text categorization. IEEE Trans Knowl Data Eng 28(9):2508\u20132521","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"4306_CR41","first-page":"012024","volume":"1192","author":"AA Farisi","year":"2019","unstructured":"Farisi AA, Sibaroni Y, Al Faraby S (2019) Sentiment analysis on hotel reviews using Multinomial Na\u0131ve Bayes classifier. J Phys Conf Ser 1192(1):012024","journal-title":"JPhysConfSer"},{"issue":"3","key":"4306_CR42","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/s11633-015-0912-z","volume":"15","author":"M Goudjil","year":"2018","unstructured":"GoudjilMet al (2018) A novel active learning method using SVM for text classification. Int J Autom Comput 15(3):290\u2013298","journal-title":"Int J Autom Comput"},{"key":"4306_CR43","doi-asserted-by":"crossref","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","DOI":"10.1023\/A:1010933404324"},{"key":"4306_CR44","doi-asserted-by":"crossref","unstructured":"Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3\u201342","DOI":"10.1007\/s10994-006-6226-1"},{"key":"4306_CR45","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"issue":"5","key":"4306_CR46","first-page":"1189","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189\u20131232","journal-title":"AnnStat"},{"key":"4306_CR47","doi-asserted-by":"crossref","unstructured":"Huang G et al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"4306_CR48","doi-asserted-by":"crossref","unstructured":"Zoph B et al (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"},{"key":"4306_CR49","doi-asserted-by":"crossref","unstructured":"Radhika K et al (2020) Performance analysis of NASNet on unconstrained ear recognition. In: Nature inspired computing for data science, Springer, pp 57\u201382","DOI":"10.1007\/978-3-030-33820-6_3"},{"key":"4306_CR50","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"4306_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy C et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4306_CR52","unstructured":"Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning, PMLR, pp 6105\u20136114"},{"key":"4306_CR53","doi-asserted-by":"crossref","unstructured":"He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"4306_CR54","doi-asserted-by":"crossref","unstructured":"Prashanth B, Mendu M, Thallapalli R (2021) Cloud based Machine learning with advanced predictive Analytics using Google Colaboratory. Materials today: proceedings, Elsevier","DOI":"10.1016\/j.matpr.2021.01.800"},{"key":"4306_CR55","unstructured":"Tensorflow. https:\/\/www.tensorflow.org\/. Accessed18June2021"},{"key":"4306_CR56","unstructured":"ScikitLearn. https:\/\/scikit-learn.org\/stable\/. Accessed18June2021"},{"issue":"1","key":"4306_CR57","first-page":"012058","volume":"1873","author":"J Zhang","year":"2021","unstructured":"Zhang J, Guo H, Chen Z (2021) A concatenated approach based on transfer learning and PCA for classifying bees and wasps. J Phys Conf Ser 1873(1):012058","journal-title":"JPhysConfSer"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04306-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04306-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04306-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T03:55:06Z","timestamp":1685591706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04306-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,15]]},"references-count":57,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["4306"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04306-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,15]]},"assertion":[{"value":"27 October 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared no potential conflicts of interest with respect to the research, authorship, and\/or publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}