{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:29:47Z","timestamp":1758709787016,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416811"},{"type":"electronic","value":"9783031416828"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-41682-8_24","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"384-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Augraphy: A Data Augmentation Library for\u00a0Document Images"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Groleau","sequence":"first","affiliation":[]},{"given":"Kok Wei","family":"Chee","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Larson","sequence":"additional","affiliation":[]},{"given":"Samay","family":"Maini","sequence":"additional","affiliation":[]},{"given":"Jonathan","family":"Boarman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"issue":"5","key":"24_CR1","first-page":"613","volume":"44","author":"GL Albano","year":"2018","unstructured":"Albano, G.L., Sparro, M.: The role of digitalization in public service provision: evidence and implications for the efficiency of local government services. Local Gov. Stud. 44(5), 613\u2013636 (2018)","journal-title":"Local Gov. Stud."},{"issue":"4","key":"24_CR2","first-page":"2827","volume":"25","author":"F Alkhezzi","year":"2020","unstructured":"Alkhezzi, F., Alsabawy, A.Y.: Factors influencing the implementation of learning management systems in higher education: a case study. Educ. Inf. Technol. 25(4), 2827\u20132845 (2020)","journal-title":"Educ. Inf. Technol."},{"doi-asserted-by":"crossref","unstructured":"Arlazarov, V., Bulatov, K., Chernov, T., Arlazarov, V.: MIDV-500: a dataset for indentity document analysis and recognition on mobile devices in video stream. Comput. Optics 43(5), 818\u2013824 (2019)","key":"24_CR3","DOI":"10.18287\/2412-6179-2019-43-5-818-824"},{"doi-asserted-by":"crossref","unstructured":"Bloice, M.D., Roth, P.M., Holzinger, A.: Biomedical image augmentation using Augmentor. Bioinformatics 35(21), 4522\u20134524 (2019)","key":"24_CR4","DOI":"10.1093\/bioinformatics\/btz259"},{"doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2), 125 (2020)","key":"24_CR5","DOI":"10.3390\/info11020125"},{"doi-asserted-by":"crossref","unstructured":"Cao, Y., Yu, H., Wu, J.: Training vision transformers with only 2040 images. CoRR abs\/2201.10728 (2022)","key":"24_CR6","DOI":"10.1007\/978-3-031-19806-9_13"},{"doi-asserted-by":"crossref","unstructured":"Castro-Bleda, M.J., Espa\u00f1a-Boquera, S., Pastor-Pellicer, J., Zamora-Mart\u00ednez, F.: The NoisyOffice database: a corpus to train supervised machine learning filters for image processing. Comput. J. 63(11), 1658\u20131667 (2019)","key":"24_CR7","DOI":"10.1093\/comjnl\/bxz098"},{"doi-asserted-by":"crossref","unstructured":"Chen, L., Chu, X., Zhang, X., Sun, J.: Simple baselines for image restoration. arXiv preprint arXiv:2204.04676 (2022)","key":"24_CR8","DOI":"10.1007\/978-3-031-20071-7_2"},{"doi-asserted-by":"crossref","unstructured":"Cheriet, M., Kharma, N., Liu, C.L., Suen, C.Y.: Character Recognition Systems: a Guide for Students and Practitioners. Wiley (2007)","key":"24_CR9","DOI":"10.1002\/9780470176535"},{"key":"24_CR10","volume-title":"Handbook of Blockchain, Digital Finance, and Inclusion: Cryptocurrency, FinTech, InsurTech, Regulation","author":"DLK Chuen","year":"2017","unstructured":"Chuen, D.L.K., Deng, R.H.: Handbook of Blockchain, Digital Finance, and Inclusion: Cryptocurrency, FinTech, InsurTech, Regulation. Mobile Security, and Distributed Ledger. Academic Press, ChinaTech (2017)"},{"doi-asserted-by":"crossref","unstructured":"Dodge, S., Karam, L.: Understanding how image quality affects deep neural networks. In: Proceedings of the 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX) (2016)","key":"24_CR11","DOI":"10.1109\/QoMEX.2016.7498955"},{"doi-asserted-by":"crossref","unstructured":"Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neural machine translation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2017)","key":"24_CR12","DOI":"10.18653\/v1\/P17-2090"},{"doi-asserted-by":"crossref","unstructured":"Feng, S.Y., et al.: A survey of data augmentation approaches for NLP. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics (2021)","key":"24_CR13","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"doi-asserted-by":"crossref","unstructured":"Gangeh, M.J., Plata, M., Motahari Nezhad, H.R., Duffy, N.P.: End-to-end unsupervised document image blind denoising. In: Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","key":"24_CR14","DOI":"10.1109\/ICCV48922.2021.00779"},{"issue":"3","key":"24_CR15","first-page":"385","volume":"41","author":"N Gatzert","year":"2016","unstructured":"Gatzert, N., Schmeiser, H.: The impact of various digitalization aspects on insurance value: an enterprise risk management approach. Geneva Papers Risk Insur.-Issues Pract. 41(3), 385\u2013405 (2016)","journal-title":"Geneva Papers Risk Insur.-Issues Pract."},{"unstructured":"Groleau, A., Chee, K.W., Larson, S., Maini, S., Boarman, J.: ShabbyPages: a reproducible document denoising and binarization dataset. arXiv preprint arXiv:2303.09339 (2023)","key":"24_CR16"},{"doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR) (2015)","key":"24_CR17","DOI":"10.1109\/ICDAR.2015.7333910"},{"issue":"7825","key":"24_CR18","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C.R., et al.: Array programming with NumPy. Nature 585(7825), 357\u2013362 (2020)","journal-title":"Nature"},{"unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)","key":"24_CR19"},{"unstructured":"Homeyer, A., et al.: Recommendations on test datasets for evaluating ai solutions in pathology. arXiv preprint arXiv:2204.14226 (2022)","key":"24_CR20"},{"doi-asserted-by":"crossref","unstructured":"Hosseini, H., Xiao, B., Poovendran, R.: Google\u2019s cloud vision API is not robust to noise. arXiv preprint arXiv:1704:05051 (2017)","key":"24_CR21","DOI":"10.1109\/ICMLA.2017.0-172"},{"doi-asserted-by":"crossref","unstructured":"Jadhav, P., Sawal, M., Zagade, A., Kamble, P., Deshpande, P.: Pix2Pix generative adversarial network with ResNet for document image denoising. In: Proceedings of the 4th International Conference on Inventive Research in Computing Applications (ICIRCA) (2022)","key":"24_CR22","DOI":"10.1109\/ICIRCA54612.2022.9985695"},{"unstructured":"Jain, V., Learned-Miller, E.: FDDB: a benchmark for face detection in unconstrained settings. Tech. Rep. UM-CS-2010-009, University of Massachusetts, Amherst (2010)","key":"24_CR23"},{"doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: Accepted to ICDAR-OST (2019)","key":"24_CR24","DOI":"10.1109\/ICDARW.2019.10029"},{"doi-asserted-by":"crossref","unstructured":"Journet, N., Visani, M., Mansencal, B., Van-Cuong, K., Billy, A.: DocCreator: a new software for creating synthetic ground-truthed document images. J. Imag. 3(4), 62 (2017)","key":"24_CR25","DOI":"10.3390\/jimaging3040062"},{"unstructured":"Jung, A.B., et al.: imgaug. https:\/\/github.com\/aleju\/imgaug (2020). Accessed 01 Feb 2020","key":"24_CR26"},{"doi-asserted-by":"crossref","unstructured":"Karahan, S., Kilinc Yildirum, M., Kirtac, K., Rende, F.S., Butun, G., Ekenel, H.K.: How image degradations affect deep CNN-based face recognition? In: Proceedings of the 2016 International Conference of the Biometrics Special Interest Group (BIOSIG) (2016)","key":"24_CR27","DOI":"10.1109\/BIOSIG.2016.7736924"},{"doi-asserted-by":"crossref","unstructured":"Kim, D., Hong, T., Yim, M., Kim, Y., Kim, G.: Technical report on web-based visual corpus construction for visual document understanding. arXiv preprint arXiv:2211.03256 (2022)","key":"24_CR28","DOI":"10.1007\/978-3-031-41682-8_19"},{"doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Proceedings of Interspeech 2015 (2015)","key":"24_CR29","DOI":"10.21437\/Interspeech.2015-711"},{"key":"24_CR30","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-981-15-1884-3_27","volume-title":"Machine Learning and Information Processing","author":"M Kulkarni","year":"2020","unstructured":"Kulkarni, M., Kakad, S., Mehra, R., Mehta, B.: Denoising documents using image processing for digital restoration. In: Swain, D., Pattnaik, P.K., Gupta, P.K. (eds.) Machine Learning and Information Processing. AISC, vol. 1101, pp. 287\u2013295. Springer, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-1884-3_27"},{"unstructured":"Larson, S., Lim, G., Ai, Y., Kuang, D., Leach, K.: Evaluating out-of-distribution performance on document image classifiers. In: Proceedings of the Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022)","key":"24_CR31"},{"doi-asserted-by":"crossref","unstructured":"Lee, B.C.G., et al.: The newspaper navigator dataset: extracting headlines and visual content from 16 million historic newspaper pages in chronicling America. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management (CIKM) (2020)","key":"24_CR32","DOI":"10.1145\/3340531.3412767"},{"unstructured":"Lee, S.H., Lee, S., Song, B.C.: Vision transformer for small-size datasets. arXiv preprint arXiv:2112.13492 (2021)","key":"24_CR33"},{"doi-asserted-by":"crossref","unstructured":"Maguolo, G., Paci, M., Nanni, L., Bonan, L.: Audiogmenter: a MATLAB toolbox for audio data augmentation. Applied Computing and Informatics (2021)","key":"24_CR34","DOI":"10.1108\/ACI-03-2021-0064"},{"unstructured":"McFee, B., Humphrey, E., Bello, J.: A software framework for musical data augmentation. In: Muller, M., Wiering, F. (eds.) Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015 (2015)","key":"24_CR35"},{"key":"24_CR36","doi-asserted-by":"publisher","first-page":"47","DOI":"10.2147\/RMHP.S12985","volume":"4","author":"N Menachemi","year":"2011","unstructured":"Menachemi, N., Collum, T.H.: Benefits and drawbacks of electronic health record systems. Risk Manage. Healthcare Policy 4, 47\u201355 (2011)","journal-title":"Risk Manage. Healthcare Policy"},{"doi-asserted-by":"crossref","unstructured":"Mohamed, S.S.A., Rashwan, M.A.A., Abdou, S.M., Al-Barhamtoshy, H.M.: Patch-based document denoising. In: Proceedings of the 2018 International Japan-Africa Conference on Electronics, Communications and Computations (JAC-ECC) (2018)","key":"24_CR37","DOI":"10.1109\/JEC-ECC.2018.8679566"},{"doi-asserted-by":"crossref","unstructured":"Mustafa, W.A., Kader, M.M.M.A.: Binarization of document image using optimum threshold modification. J. Phys. Confer. Ser. 1019, 012022 (2018)","key":"24_CR38","DOI":"10.1088\/1742-6596\/1019\/1\/012022"},{"unstructured":"O\u2019Gorman, L., Kasturi, R.: Document image analysis. IEEE Computer Society (1997)","key":"24_CR39"},{"doi-asserted-by":"crossref","unstructured":"Papakipos, Z., Bitton, J.: AugLy: data augmentations for robustness. arXiv preprint arXiv:2201:06494 (2022)","key":"24_CR40","DOI":"10.1109\/CVPRW56347.2022.00027"},{"unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32, pp. 8024\u20138035 (2019)","key":"24_CR41"},{"unstructured":"Rotman, D., Azulai, O., Shapira, I., Burshtein, Y., Barzelay, U.: Detection masking for improved OCR on noisy documents. arXiv preprint arXiv:2205.08257 (2022)","key":"24_CR42"},{"doi-asserted-by":"crossref","unstructured":"Saifullah, Siddiqui, S.A., Agne, S., Dengel, A., Ahmed, S.: Are deep models robust against real distortions? A case study on document image classification. In: Proceedings of the 26th International Conference on Pattern Recognition (ICPR) (2022)","key":"24_CR43","DOI":"10.1109\/ICPR56361.2022.9956167"},{"doi-asserted-by":"crossref","unstructured":"Sch\u00f6mig-Markiefka, B., et al.: Quality control stress test for deep learning-based diagnostic model in digital pathology. Modern pathol.: an official journal of the United States and Canadian Academy of Pathology, Inc 34(12), 2098\u20132108 (2021)","key":"24_CR44","DOI":"10.1038\/s41379-021-00859-x"},{"doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 629\u2013633. IEEE (2007)","key":"24_CR45","DOI":"10.1109\/ICDAR.2007.4376991"},{"issue":"3","key":"24_CR46","first-page":"695","volume":"88","author":"RW Staudt","year":"2015","unstructured":"Staudt, R.W., Medeiros, A.P.: Access to justice and technology clinics: a 4% solution. Chicago-Kent Law Rev. 88(3), 695\u2013728 (2015)","journal-title":"Chicago-Kent Law Rev."},{"unstructured":"Vasiljevic, I., Chakrabarti, A., Shakhnarovich, G.: Examining the impact of blur on recognition by convolutional networks. arXiv preprint arXiv:1611.05760 (2016)","key":"24_CR47"},{"doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics (2019)","key":"24_CR48","DOI":"10.18653\/v1\/D19-1670"},{"unstructured":"Zamora-Mart\u00ednez, F., Espa\u00f1a Boquera, S., Castro-Bleda, M.: Behaviour-based clustering of neural networks applied to document enhancement. In: Computational and Ambient Intelligence (2007)","key":"24_CR49"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41682-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T07:12:51Z","timestamp":1702969971000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41682-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416811","9783031416828"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41682-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}