{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:41:37Z","timestamp":1740102097059,"version":"3.37.3"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417337"},{"type":"electronic","value":"9783031417344"}],"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\/978-3-031-41734-4_19","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"305-324","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["UTRNet: High-Resolution Urdu Text Recognition in\u00a0Printed Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9547-2435","authenticated-orcid":false,"given":"Abdur","family":"Rahman","sequence":"first","affiliation":[]},{"given":"Arjun","family":"Ghosh","sequence":"additional","affiliation":[]},{"given":"Chetan","family":"Arora","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"19_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S.B., Naz, S., Swati, S., Razzak, M.I.: Handwritten Urdu character recognition using 1-dimensional blstm classifier (2017). https:\/\/doi.org\/10.48550\/ARXIV.1705.05455","DOI":"10.48550\/ARXIV.1705.05455"},{"key":"19_CR2","unstructured":"Akram, M.U., Hussain, S.: Word segmentation for Urdu ocr system (2010)"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2352\/J.ImagingSci.Technol.2019.63.2.020502","volume":"63","author":"JM Alghazo","year":"2019","unstructured":"Alghazo, J.M., Latif, G., Alzubaidi, L., Elhassan, A.: Multi-language handwritten digits recognition based on novel structural features. J. Imaging Sci. Technol. 63, 1\u201310 (2019)","journal-title":"J. Imaging Sci. Technol."},{"key":"19_CR4","doi-asserted-by":"publisher","unstructured":"Ali, A., Pickering, M.: Urdu-text: a dataset and benchmark for Urdu text detection and recognition in natural scenes. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 323\u2013328 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00059","DOI":"10.1109\/ICDAR.2019.00059"},{"key":"19_CR5","doi-asserted-by":"publisher","unstructured":"Althobaiti, H., Lu, C.: A survey on Arabic optical character recognition and an isolated handwritten Arabic character recognition algorithm using encoded freeman chain code. In: 2017 51st Annual Conference on Information Sciences and Systems (CISS), pp. 1\u20136 (2017). https:\/\/doi.org\/10.1109\/CISS.2017.7926062","DOI":"10.1109\/CISS.2017.7926062"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Anjum, T., Khan, N.: An attention based method for offline handwritten Urdu text recognition. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 169\u2013174 (2020). https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00040","DOI":"10.1109\/ICFHR2020.2020.00040"},{"key":"19_CR7","doi-asserted-by":"publisher","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition (2021). https:\/\/doi.org\/10.48550\/ARXIV.2105.08582. https:\/\/arxiv.org\/abs\/2105.08582","DOI":"10.48550\/ARXIV.2105.08582"},{"key":"19_CR8","doi-asserted-by":"publisher","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis (2019). https:\/\/doi.org\/10.48550\/ARXIV.1904.01906","DOI":"10.48550\/ARXIV.1904.01906"},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). https:\/\/doi.org\/10.48550\/ARXIV.1409.0473","DOI":"10.48550\/ARXIV.1409.0473"},{"key":"19_CR10","doi-asserted-by":"publisher","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models (2022). https:\/\/doi.org\/10.48550\/ARXIV.2207.06966. https:\/\/arxiv.org\/abs\/2207.06966","DOI":"10.48550\/ARXIV.2207.06966"},{"key":"19_CR11","doi-asserted-by":"publisher","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM (2018). https:\/\/doi.org\/10.1145\/3219819.3219861","DOI":"10.1145\/3219819.3219861"},{"key":"19_CR12","doi-asserted-by":"publisher","first-page":"520","DOI":"10.3390\/forecast3030033","volume":"3","author":"H Butt","year":"2021","unstructured":"Butt, H., Raza, M.R., Ramzan, M., Ali, M.J., Haris, M.: Attention-based cnn-rnn Arabic text recognition from natural scene images. Forecasting 3, 520\u2013540 (2021). https:\/\/doi.org\/10.3390\/forecast3030033","journal-title":"Forecasting"},{"key":"19_CR13","doi-asserted-by":"publisher","unstructured":"Byeon, W., Liwicki, M., Breuel, T.M.: Texture classification using 2D LSTM networks. In: 2014 22nd International Conference on Pattern Recognition, pp. 1144\u20131149 (2014). https:\/\/doi.org\/10.1109\/ICPR.2014.206","DOI":"10.1109\/ICPR.2014.206"},{"key":"19_CR14","unstructured":"Chammas, E., Mokbel, C.: Fine-tuning handwriting recognition systems with temporal dropout (2021). ArXiv abs\/2102.00511 https:\/\/arxiv.org\/abs\/2102.00511"},{"key":"19_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.105749","volume":"31","author":"AA Chandio","year":"2020","unstructured":"Chandio, A.A., Asikuzzaman, M., Pickering, M., Leghari, M.: Cursive-text: a comprehensive dataset for end-to-end Urdu text recognition in natural scene images. Data Brief 31, 105749 (2020). https:\/\/doi.org\/10.1016\/j.dib.2020.105749","journal-title":"Data Brief"},{"key":"19_CR16","doi-asserted-by":"publisher","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches (2014). https:\/\/doi.org\/10.48550\/ARXIV.1409.1259","DOI":"10.48550\/ARXIV.1409.1259"},{"key":"19_CR17","doi-asserted-by":"publisher","unstructured":"Choudhary, P., Nain, N.: A four-tier annotated Urdu handwritten text image dataset for multidisciplinary research on Urdu script. ACM Trans. Asian Low Res. Lang. Inf. Process. 15(4), 1\u201323 (2016). https:\/\/doi.org\/10.1145\/2857053","DOI":"10.1145\/2857053"},{"key":"19_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJAIML.20210701.oa9","volume":"11","author":"S Djaghbellou","year":"2021","unstructured":"Djaghbellou, S., Bouziane, A., Attia, A., Akhtar, Z.: A survey on Arabic handwritten script recognition systems. Int. J. Artif. Intell. Mach. Learn. 11, 1\u201317 (2021). https:\/\/doi.org\/10.4018\/IJAIML.20210701.oa9","journal-title":"Int. J. Artif. Intell. Mach. Learn."},{"key":"19_CR19","doi-asserted-by":"publisher","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition (2021). https:\/\/doi.org\/10.48550\/ARXIV.2103.06495. https:\/\/arxiv.org\/abs\/2103.06495","DOI":"10.48550\/ARXIV.2103.06495"},{"key":"19_CR20","unstructured":"Fasha, M., Hammo, B.H., Obeid, N., Widian, J.: A hybrid deep learning model for Arabic text recognition (2020). ArXiv abs\/2009.01987 https:\/\/arxiv.org\/abs\/2009.01987"},{"key":"19_CR21","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation (2013). https:\/\/doi.org\/10.48550\/ARXIV.1311.2524","DOI":"10.48550\/ARXIV.1311.2524"},{"key":"19_CR22","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, p. 369\u2013376 (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"19_CR23","unstructured":"Graves, A., Schmidhuber, J.: Offline Arabic handwriting recognition with multidimensional recurrent neural networks, pp. 545\u2013552 (2008)"},{"issue":"1","key":"19_CR24","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"Han, K., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3152247","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR25","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https:\/\/doi.org\/10.48550\/ARXIV.1512.03385","DOI":"10.48550\/ARXIV.1512.03385"},{"key":"19_CR26","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks (2016). https:\/\/doi.org\/10.48550\/ARXIV.1608.06993","DOI":"10.48550\/ARXIV.1608.06993"},{"issue":"11","key":"19_CR27","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1049\/iet-ipr.2019.0401","volume":"14","author":"M Husnain","year":"2020","unstructured":"Husnain, M., Saad Missen, M.M., Mumtaz, S., Coustaty, M., Luqman, M., Ogier, J.M.: Urdu handwritten text recognition: a survey. IET Image Process. 14(11), 2291\u20132300 (2020). https:\/\/doi.org\/10.1049\/iet-ipr.2019.0401","journal-title":"IET Image Process."},{"key":"19_CR28","doi-asserted-by":"publisher","first-page":"27","DOI":"10.3390\/app13074584","volume":"13","author":"S Hussain","year":"2023","unstructured":"Hussain, S.: A survey of ocr in Arabic language: applications, techniques, and challenges. Appl. Sci. 13, 27 (2023). https:\/\/doi.org\/10.3390\/app13074584","journal-title":"Appl. Sci."},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Jain, M., Mathew, M., Jawahar, C.V.: Unconstrained scene text and video text recognition for Arabic script. In: 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), pp. 26\u201330 (2017)","DOI":"10.1109\/ASAR.2017.8067754"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Jain, M., Mathew, M., Jawahar, C.: Unconstrained ocr for Urdu using deep cnn-rnn hybrid networks. In: 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), pp. 747\u2013752. IEEE (2017)","DOI":"10.1109\/ACPR.2017.5"},{"key":"19_CR31","doi-asserted-by":"publisher","unstructured":"Kashif, M.: Urdu handwritten text recognition using resnet18 (2021). https:\/\/doi.org\/10.48550\/ARXIV.2103.05105","DOI":"10.48550\/ARXIV.2103.05105"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Kassem, A.M., et al.: Ocformer: a transformer-based model for Arabic handwritten text recognition. In: 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), pp. 182\u2013186 (2021)","DOI":"10.1109\/MIUCC52538.2021.9447608"},{"key":"19_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5120\/9733-2082","volume":"60","author":"K Khan","year":"2012","unstructured":"Khan, K., Ullah, R., Ahmad, N., Naveed, K.: Urdu character recognition using principal component analysis. Int. J. Comput. Appl. 60, 1\u20134 (2012). https:\/\/doi.org\/10.5120\/9733-2082","journal-title":"Int. J. Comput. Appl."},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"46019","DOI":"10.1109\/ACCESS.2018.2865532","volume":"6","author":"NH Khan","year":"2018","unstructured":"Khan, N.H., Adnan, A.: Urdu optical character recognition systems: present contributions and future directions. IEEE Access 6, 46019\u201346046 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2018.2865532","journal-title":"IEEE Access"},{"key":"19_CR35","unstructured":"Khan, N.H., Adnan, A., Basar, S.: An analysis of off-line and on-line approaches in Urdu character recognition. In: 2016 15th International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases (AIKED 2016) (2016)"},{"key":"19_CR36","doi-asserted-by":"publisher","first-page":"176-1","DOI":"10.2352\/ISSN.2470-1173.2018.2.VIPC-176","volume":"2018","author":"D Ko","year":"2018","unstructured":"Ko, D., Lee, C., Han, D., Ohk, H., Kang, K., Han, S.: Approach for machine-printed Arabic character recognition: the-state-of-the-art deep-learning method. Electron. Imaging 2018, 176-1\u2013176-8 (2018)","journal-title":"Electron. Imaging"},{"key":"19_CR37","unstructured":"Kolesnikov, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2021)"},{"issue":"11","key":"19_CR38","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"key":"19_CR39","doi-asserted-by":"publisher","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for ocr in the wild (2016). https:\/\/doi.org\/10.48550\/ARXIV.1603.03101. https:\/\/arxiv.org\/abs\/1603.03101","DOI":"10.48550\/ARXIV.1603.03101"},{"key":"19_CR40","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: Trocr: transformer-based optical character recognition with pre-trained models (2021). https:\/\/doi.org\/10.48550\/ARXIV.2109.10282. https:\/\/arxiv.org\/abs\/2109.10282","DOI":"10.48550\/ARXIV.2109.10282"},{"key":"19_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR42","doi-asserted-by":"publisher","unstructured":"Liu, W., Chen, C., Wong, K.Y., Su, Z., Han, J.: Star-net: A spatial attention residue network for scene text recognition, pp. 43.1\u201343.13 (2016). https:\/\/doi.org\/10.5244\/C.30.43","DOI":"10.5244\/C.30.43"},{"issue":"22","key":"19_CR43","doi-asserted-by":"publisher","first-page":"15229","DOI":"10.1007\/s00521-021-06144-x","volume":"33","author":"F Mushtaq","year":"2021","unstructured":"Mushtaq, F., Misgar, M.M., Kumar, M., Khurana, S.S.: UrduDeepNet: offline handwritten Urdu character recognition using deep neural network. Neural Comput. Appl. 33(22), 15229\u201315252 (2021)","journal-title":"Neural Comput. Appl."},{"key":"19_CR44","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.procs.2016.08.084","volume":"96","author":"S Naz","year":"2016","unstructured":"Naz, S., Ahmed, S., Ahmad, R., Razzak, M.: Zoning features and 2dlstm for Urdu text-line recognition. Procedia Comput. Sci. 96, 16\u201322 (2016). https:\/\/doi.org\/10.1016\/j.procs.2016.08.084","journal-title":"Procedia Comput. Sci."},{"key":"19_CR45","doi-asserted-by":"publisher","unstructured":"Naz, S., et al.: Urdu nastaliq recognition using convolutional-recursive deep learning. Neurocomputing 243, 80\u201387 (2017). https:\/\/doi.org\/10.1016\/j.neucom.2017.02.081. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231217304654","DOI":"10.1016\/j.neucom.2017.02.081"},{"key":"19_CR46","doi-asserted-by":"publisher","unstructured":"Oktay, O., et al.: Attention u-net: learning where to look for the pancreas (2018). https:\/\/doi.org\/10.48550\/ARXIV.1804.03999","DOI":"10.48550\/ARXIV.1804.03999"},{"key":"19_CR47","doi-asserted-by":"publisher","unstructured":"Pal, U., Sarkar, A.: Recognition of printed Urdu script. In: Seventh International Conference on Document Analysis and Recognition, 2003, Proceedings, pp. 1183\u20131187 (2003). https:\/\/doi.org\/10.1109\/ICDAR.2003.1227844","DOI":"10.1109\/ICDAR.2003.1227844"},{"issue":"1","key":"19_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3376922","volume":"16","author":"NS Punn","year":"2020","unstructured":"Punn, N.S., Agarwal, S.: Inception u-net architecture for semantic segmentation to identify nuclei in microscopy cell images. ACM Trans. Multimedia Comput. Commun. Appl. 16(1), 1\u201315 (2020). https:\/\/doi.org\/10.1145\/3376922","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"19_CR49","doi-asserted-by":"publisher","unstructured":"Rashid, S.F., Schambach, M.P., Rottland, J., N\u00fcll, S.: Low resolution Arabic recognition with multidimensional recurrent neural networks (2013). https:\/\/doi.org\/10.1145\/2505377.2505385","DOI":"10.1145\/2505377.2505385"},{"key":"19_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"19_CR51","doi-asserted-by":"publisher","unstructured":"Sabbour, N., Shafait, F.: A segmentation free approach to Arabic and Urdu ocr. In: Proceedings of SPIE - The International Society for Optical Engineering, vol. 8658 (2013). https:\/\/doi.org\/10.1117\/12.2003731","DOI":"10.1117\/12.2003731"},{"key":"19_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/978-3-642-04146-4_58","volume-title":"Image Analysis and Processing \u2013 ICIAP 2009","author":"MW Sagheer","year":"2009","unstructured":"Sagheer, M.W., He, C.L., Nobile, N., Suen, C.Y.: A new large Urdu database for off-line handwriting recognition. In: Foggia, P., Sansone, C., Vento, M. (eds.) ICIAP 2009. LNCS, vol. 5716, pp. 538\u2013546. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04146-4_58"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Sardar, S., Wahab, A.: Optical character recognition system for Urdu. In: 2010 International Conference on Information and Emerging Technologies, pp. 1\u20135 (2010)","DOI":"10.1109\/ICIET.2010.5625694"},{"issue":"11","key":"19_CR54","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Semary, N., Rashad, M.: Isolated printed Arabic character recognition using knn and random forest tree classifiers, vol. 488, p. 11 (2014)","DOI":"10.1007\/978-3-319-13461-1_2"},{"key":"19_CR56","doi-asserted-by":"publisher","unstructured":"Shahin, A.: Printed Arabic text recognition using linear and nonlinear regression. Int. J. Adv. Comput. Sci. Appl. 8 (2017). https:\/\/doi.org\/10.14569\/IJACSA.2017.080129","DOI":"10.14569\/IJACSA.2017.080129"},{"key":"19_CR57","doi-asserted-by":"publisher","unstructured":"Shaiq, M.D., Cheema, M.D.A., Kamal, A.: Transformer based Urdu handwritten text optical character reader (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.04575. https:\/\/arxiv.org\/abs\/2206.04575","DOI":"10.48550\/ARXIV.2206.04575"},{"key":"19_CR58","doi-asserted-by":"publisher","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition (2015). https:\/\/doi.org\/10.48550\/ARXIV.1507.05717","DOI":"10.48550\/ARXIV.1507.05717"},{"key":"19_CR59","doi-asserted-by":"publisher","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification (2016). https:\/\/doi.org\/10.48550\/ARXIV.1603.03915. https:\/\/arxiv.org\/abs\/1603.03915","DOI":"10.48550\/ARXIV.1603.03915"},{"key":"19_CR60","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). https:\/\/doi.org\/10.48550\/ARXIV.1409.1556","DOI":"10.48550\/ARXIV.1409.1556"},{"key":"19_CR61","doi-asserted-by":"publisher","first-page":"314","DOI":"10.7763\/IJMLC.2012.V2.137","volume":"2","author":"A Singh","year":"2012","unstructured":"Singh, A., Bacchuwar, K., Bhasin, A.: A survey of OCR applications. Int. J. Mach. Learn. Comput. (IJMLC) 2, 314 (2012). https:\/\/doi.org\/10.7763\/IJMLC.2012.V2.137","journal-title":"Int. J. Mach. Learn. Comput. (IJMLC)"},{"key":"19_CR62","doi-asserted-by":"publisher","unstructured":"Sobhi, M., Hifny, Y., Elkaffas, S.M.: Arabic optical character recognition using attention based encoder-decoder architecture. In: 2020 2nd International Conference on Artificial Intelligence, Robotics and Control, AIRC 2020, pp. 1\u20135. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3448326.3448327","DOI":"10.1145\/3448326.3448327"},{"key":"19_CR63","doi-asserted-by":"publisher","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks (2014). https:\/\/doi.org\/10.48550\/ARXIV.1409.3215. https:\/\/arxiv.org\/abs\/1409.3215","DOI":"10.48550\/ARXIV.1409.3215"},{"key":"19_CR64","first-page":"92","volume":"3","author":"N Tabassam","year":"2009","unstructured":"Tabassam, N., Naqvi, S., Rehman, H., Anoshia, F.: Optical character recognition system for Urdu (Naskh font) using pattern matching technique. Int. J. Image Process. 3, 92 (2009)","journal-title":"Int. J. Image Process."},{"key":"19_CR65","unstructured":"Wang, J., Hu, X.: Gated recurrent convolution neural network for ocr. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 334\u2013343. Curran Associates Inc., Red Hook (2017)"},{"key":"19_CR66","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition (2019)"},{"key":"19_CR67","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: Shape robust text detection with progressive scale expansion network (2019). https:\/\/doi.org\/10.48550\/ARXIV.1903.12473","DOI":"10.48550\/ARXIV.1903.12473"},{"key":"19_CR68","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network (2021). https:\/\/doi.org\/10.48550\/ARXIV.2108.09661. https:\/\/arxiv.org\/abs\/2108.09661","DOI":"10.48550\/ARXIV.2108.09661"},{"key":"19_CR69","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xie, H., Zha, Z., Xing, M., Fu, Z., Zhang, Y.: Contournet: taking a further step toward accurate arbitrary-shaped scene text detection (2020). https:\/\/doi.org\/10.48550\/ARXIV.2004.04940","DOI":"10.48550\/ARXIV.2004.04940"},{"key":"19_CR70","doi-asserted-by":"publisher","unstructured":"Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet (2021). https:\/\/doi.org\/10.48550\/ARXIV.2101.11986. https:\/\/arxiv.org\/abs\/2101.11986","DOI":"10.48550\/ARXIV.2101.11986"},{"key":"19_CR71","doi-asserted-by":"publisher","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method (2012). https:\/\/doi.org\/10.48550\/ARXIV.1212.5701","DOI":"10.48550\/ARXIV.1212.5701"},{"key":"19_CR72","doi-asserted-by":"publisher","unstructured":"Zhang, S.X., et al.: Deep relational reasoning graph network for arbitrary shape text detection (2020). https:\/\/doi.org\/10.48550\/ARXIV.2003.07493","DOI":"10.48550\/ARXIV.2003.07493"},{"key":"19_CR73","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Liu, Q., Wang, Y.: Road extraction by deep residual u-net. IEEE Geosci. Remote Sens. Lett. 15(5), 749\u2013753 (2018). https:\/\/doi.org\/10.1109\/lgrs.2018.2802944","DOI":"10.1109\/lgrs.2018.2802944"},{"key":"19_CR74","doi-asserted-by":"publisher","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., Jiang, Y.G.: Cdistnet: perceiving multi-domain character distance for robust text recognition (2021). https:\/\/doi.org\/10.48550\/ARXIV.2111.11011. https:\/\/arxiv.org\/abs\/2111.11011","DOI":"10.48550\/ARXIV.2111.11011"},{"key":"19_CR75","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector (2017). https:\/\/doi.org\/10.48550\/ARXIV.1704.03155","DOI":"10.48550\/ARXIV.1704.03155"},{"key":"19_CR76","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: Unet++: a nested u-net architecture for medical image segmentation (2018). https:\/\/doi.org\/10.48550\/ARXIV.1807.10165","DOI":"10.48550\/ARXIV.1807.10165"},{"key":"19_CR77","doi-asserted-by":"crossref","unstructured":"Zoizou, A., Zarghili, A., Chaker, I.: A new hybrid method for Arabic multi-font text segmentation, and a reference corpus construction. J. King Saud Univ. Comput. Inf. Sci. 32, 576\u2013582 (2020)","DOI":"10.1016\/j.jksuci.2018.07.003"}],"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\/978-3-031-41734-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:39:19Z","timestamp":1729935559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41734-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417337","9783031417344"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41734-4_19","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)"}}]}}