{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:41:57Z","timestamp":1763142117018,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416750"},{"type":"electronic","value":"9783031416767"}],"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\/978-3-031-41676-7_3","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"45-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["TransDocAnalyser: A Framework for\u00a0Semi-structured Offline Handwritten Documents Analysis with\u00a0an\u00a0Application to\u00a0Legal Domain"],"prefix":"10.1007","author":[{"given":"Sagar","family":"Chakraborty","sequence":"first","affiliation":[]},{"given":"Gaurav","family":"Harit","sequence":"additional","affiliation":[]},{"given":"Saptarshi","family":"Ghosh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"3_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/3-540-45869-7_32","volume-title":"Document Analysis Systems V","author":"A Amano","year":"2002","unstructured":"Amano, A., Asada, N.: Complex table form analysis using graph grammar. In: Lopresti, D., Hu, J., Kashi, R. (eds.) DAS 2002. LNCS, vol. 2423, pp. 283\u2013286. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45869-7_32"},{"key":"3_CR2","doi-asserted-by":"publisher","unstructured":"Amano, A., Asada, N., Mukunoki, M., Aoyama, M.: Table form document analysis based on the document structure grammar. Int. J. Doc. Anal. Recogn. (IJDAR) 8, 210\u2013213 (2006). https:\/\/doi.org\/10.1007\/s10032-005-0008-3","DOI":"10.1007\/s10032-005-0008-3"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Bag, S., Harit, G.: A medial axis based thinning strategy and structural feature extraction of character images. In: Proceedings of IEEE International Conference on Image Processing, pp. 2173\u20132176 (2010)","DOI":"10.1109\/ICIP.2010.5654311"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Bag, S., Harit, G.: An improved contour-based thinning method for character images. Pattern Recogn. Lett. 32(14), 1836\u20131842 (2011)","DOI":"10.1016\/j.patrec.2011.07.001"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Bag, S., Harit, G.: Topographic feature extraction for Bengali and Hindi character images. Sig. Image Process. Int. J. 2, 2215 (2011)","DOI":"10.5121\/sipij.2011.2215"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharya, P., Hiware, K., Rajgaria, S., Pochhi, N., Ghosh, K., Ghosh, S.: A comparative study of summarization algorithms applied to legal case judgments. In: Proceedings of European Conference on Information Retrieval (ECIR), pp. 413\u2013428 (2019)","DOI":"10.1007\/978-3-030-15712-8_27"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1016\/j.proeng.2014.03.129","volume":"69","author":"T Bruno","year":"2014","unstructured":"Bruno, T., Sasa, M., Donko, D.: KNN with TF-IDF based framework for text categorization. Procedia Eng. 69, 1356\u20131364 (2014)","journal-title":"Procedia Eng."},{"key":"3_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"3_CR9","unstructured":"Chowdhury, A., Vig, L.: An efficient end-to-end neural model for handwritten text recognition. In: British Machine Vision Conference (2018)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Constum, T., et al.: Recognition and information extraction in historical handwritten tables: Toward understanding early 20th century Paris census. In: Proceedings of IAPR Workshop on Document Analysis Systems (DAS), pp. 143\u2013157 (2022)","DOI":"10.1007\/978-3-031-06555-2_10"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Diesendruck, L., Marini, L., Kooper, R., Kejriwal, M., McHenry, K.: A framework to access handwritten information within large digitized paper collections. In: Proceedings of IEEE International Conference on E-Science, pp. 1\u201310 (10 2012)","DOI":"10.1109\/eScience.2012.6404434"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Divya, S., Gaurav, H.: Associating field components in heterogeneous handwritten form images using graph autoencoder. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 5, pp. 41\u201346 (2019)","DOI":"10.1109\/ICDARW.2019.40079"},{"key":"3_CR13","unstructured":"Duong, Q., H\u00e4m\u00e4l\u00e4inen, M., Hengchen, S.: An unsupervised method for OCR post-correction and spelling normalisation for Finnish. In: Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pp. 240\u2013248 (2021)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Ha, H.T., Medved\u2019, M., Nev\u011b\u0159ilov\u00e1, Z., Hor\u00e1k, A.: Recognition of OCR invoice metadata block types. In: Proceedings of Text, Speech, and Dialogue, pp. 304\u2013312 (2018)","DOI":"10.1007\/978-3-030-00794-2_33"},{"key":"3_CR17","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: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995 (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"1","key":"3_CR19","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1007\/s42001-021-00149-1","volume":"5","author":"T Hegghammer","year":"2022","unstructured":"Hegghammer, T.: OCR with tesseract, Amazon textract, and google document AI: a benchmarking experiment. J. Comput. Soc. Sci. 5(1), 861\u2013882 (2022)","journal-title":"J. Comput. Soc. Sci."},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Competition on scanned receipt OCR and information extraction. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520 (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Jaume, G., Kemal Ekenel, H., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 1\u20136 (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"3_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: Proceedings of AAAI (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn. 5, 39\u201346 (2002)","DOI":"10.1007\/s100320200071"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., Z\u00f6llner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1286\u20131293 (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Palm, R.B., Winther, O., Laws, F.: CloudScan - a configuration-free invoice analysis system using recurrent neural networks. In: Proceedings of IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 406\u2013413 (2017)","DOI":"10.1109\/ICDAR.2017.74"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Paul, S., Goyal, P., Ghosh, S.: LeSICiN: a heterogeneous graph-based approach for automatic legal statute identification from Indian legal documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36 (2022)","DOI":"10.1609\/aaai.v36i10.21363"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Paul, S., Mandal, A., Goyal, P., Ghosh, S.: Pre-trained language models for the legal domain: a case study on Indian law. In: Proceedings of the International Conference on Artificial Intelligence and Law (ICAIL) (2023)","DOI":"10.1145\/3594536.3595165"},{"key":"3_CR33","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the International Conference on Neural Information Processing Systems - vol. 1, pp. 91\u201399. MIT Press (2015)"},{"key":"3_CR34","unstructured":"Subramani, N., Matton, A., Greaves, M., Lam, A.: A survey of deep learning approaches for OCR and document understanding. CoRR abs\/2011.13534 (2020)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10778\u201310787 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Watanabe, T., Luo, Q., Sugie, N.: Layout recognition of multi-kinds of table-form documents. IEEE Trans. Pattern Anal. Mach. Intell. 17(4), 432\u2013445 (1995)","DOI":"10.1109\/34.385976"},{"key":"3_CR37","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)"}],"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\/978-3-031-41676-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T07:06:51Z","timestamp":1702969611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41676-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416750","9783031416767"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41676-7_3","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)"}}]}}