{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T07:45:03Z","timestamp":1775807103479,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100018267","name":"National Institute of Technology Srinagar","doi-asserted-by":"publisher","award":["2017PHAECE007"],"award-info":[{"award-number":["2017PHAECE007"]}],"id":[{"id":"10.13039\/100018267","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018267","name":"National Institute of Technology Srinagar","doi-asserted-by":"publisher","award":["2017PHAECE007"],"award-info":[{"award-number":["2017PHAECE007"]}],"id":[{"id":"10.13039\/100018267","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10032-025-00544-8","type":"journal-article","created":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T09:10:37Z","timestamp":1752311437000},"page":"191-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards automatic efficient recognition of multiresolution offline handwritten Urdu text using swin transformers"],"prefix":"10.1007","volume":"29","author":[{"given":"Aejaz Farooq","family":"Ganai","sequence":"first","affiliation":[]},{"given":"Nasir N.","family":"Hurrah","sequence":"additional","affiliation":[]},{"given":"Farida","family":"Khursheed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"issue":"1","key":"544_CR1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1002\/aris.1440370103","volume":"37","author":"GG Chowdhury","year":"2005","unstructured":"Chowdhury, G.G.: Natural language processing. Ann. Rev. Info. Sci. Tech. 37(1), 51\u201389 (2005). https:\/\/doi.org\/10.1002\/aris.1440370103","journal-title":"Ann. Rev. Info. Sci. Tech."},{"key":"544_CR2","doi-asserted-by":"publisher","unstructured":"Obulesu, O., Mahendra, M., ThrilokReddy, M.: Machine learning techniques and tools: a survey. In: 2018 international conference on inventive research in computing applications (ICIRCA), pp. 605\u2013611. IEEE (2018). https:\/\/doi.org\/10.1109\/ICIRCA.2018.8597302.","DOI":"10.1109\/ICIRCA.2018.8597302"},{"key":"544_CR3","unstructured":"Eikvil, L.: Optical character recognition, Citeseer.ist.psu.edu\/142042.html, vol. 26 (1993)"},{"key":"544_CR4","doi-asserted-by":"publisher","unstructured":"Peng X. et al.: Multilingual OCR research and applications: an overview. In: Proc. 4th International Workshop on Multilingual OCR, pp. 1\u20138 (2013). https:\/\/doi.org\/10.1145\/2505377.2509977.","DOI":"10.1145\/2505377.2509977"},{"key":"544_CR5","doi-asserted-by":"crossref","unstructured":"Kompalli, S. et al.: Challenges in OCR of Devanagari documents. In: Eighth International Conference on Document Analysis and Recognition (ICDAR \u201905), pp. 327\u2013331 (IEEE, 2005).","DOI":"10.1109\/ICDAR.2005.70"},{"key":"544_CR6","doi-asserted-by":"publisher","unstructured":"Sabbour, N., Shafait, F.: A segmentation-free approach to Arabic and Urdu OCR. In: SPIE Proceedings, vol. 8658, International Society for Optics and Photonics (2013). https:\/\/doi.org\/10.1117\/12.2003731.","DOI":"10.1117\/12.2003731"},{"key":"544_CR7","unstructured":"Dhanashree, Top 6 Urdu OCR software in 2023. Available at: https:\/\/nanonets.com\/blog\/top-urdu-ocr-software\/. (2023)"},{"key":"544_CR8","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":"544_CR9","unstructured":"Satti, D. A., Saleem, K.: Complexities and implementation challenges in offline Urdu Nastaliq OCR. In: Proc. Conference on Language & Technology, pp. 85\u201391 (2012)."},{"issue":"2","key":"544_CR10","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1007\/s00521-021-06498-2","volume":"34","author":"N ulSehr Zia","year":"2022","unstructured":"ulSehr Zia, N., et al.: A convolutional recursive deep architecture for unconstrained Urdu handwriting recognition. Neural Comput. Appl. 34(2), 1635\u20131648 (2022). https:\/\/doi.org\/10.1007\/s00521-021-06498-2","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"544_CR11","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s13640-017-0208-z","volume":"2017","author":"IU Din","year":"2017","unstructured":"Din, I.U., et al.: Holistic optical character recognition for printed Urdu text. EURASIP J. Image Video Process. 2017(1), 62 (2017)","journal-title":"EURASIP J. Image Video Process."},{"key":"544_CR12","doi-asserted-by":"publisher","unstructured":"Lehal, G. S.: Choice of recognizable units for Urdu OCR. In: Proceeding of the Workshop on Document Analysis and Recognition, pp. 79\u201385 (2012). https:\/\/doi.org\/10.1145\/2432553.2432569.","DOI":"10.1145\/2432553.2432569"},{"issue":"2","key":"544_CR13","first-page":"239","volume":"14","author":"SB Ahmed","year":"2017","unstructured":"Ahmed, S. B. et al.: UCOM offline dataset-an Urdu handwritten dataset generation. Int. Arab J. Inf. Technol. (IAJIT). 14(2), 239\u2013245, (2017)","journal-title":"Int. Arab J. Inf. Technol. (IAJIT)"},{"issue":"4","key":"544_CR14","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1007\/s00521-017-3146-x","volume":"31","author":"SB Ahmed","year":"2019","unstructured":"Ahmed, S.B., et al.: Handwritten Urdu character recognition using one-dimensional BLSTM classifier. Neural Comput. Appl. 31(4), 1143\u20131151 (2019). https:\/\/doi.org\/10.1007\/s00521-017-3146-x","journal-title":"Neural Comput. Appl."},{"issue":"13","key":"544_CR15","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.3390\/app9132758","volume":"9","author":"M Husnain","year":"2019","unstructured":"Husnain, M., et al.: Recognition of Urdu handwritten characters using convolutional neural network. Appl. Sci. 9(13), 2758 (2019). https:\/\/doi.org\/10.3390\/app9132758","journal-title":"Appl. Sci."},{"key":"544_CR16","doi-asserted-by":"publisher","unstructured":"Hassan, S. et al.: Cursive handwritten text recognition using bi-directional LSTMs: a case study on Urdu handwriting. In: International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML), vol. 2019, pp. 67\u201372 (IEEE, 2019). https:\/\/doi.org\/10.1109\/Deep-ML.2019.00021.","DOI":"10.1109\/Deep-ML.2019.00021"},{"key":"544_CR17","doi-asserted-by":"publisher","first-page":"153566","DOI":"10.1109\/ACCESS.2019.2946313","volume":"7","author":"SB Ahmed","year":"2019","unstructured":"Ahmed, S.B., et al.: Evaluation of handwritten Urdu text by integration of MNIST dataset learning experience. IEEE Access 7, 153566\u2013153578 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2946313","journal-title":"IEEE Access"},{"issue":"4","key":"544_CR18","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s10032-022-00414-7","volume":"25","author":"AF Ganai","year":"2022","unstructured":"Ganai, A.F., Khursheed, F.: A novel holistic unconstrained handwritten urdu recognition system using convolutional neural networks. Int. J. Doc. Anal. Recogn. (IJDAR) 25(4), 351\u2013371 (2022)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"544_CR19","unstructured":"Shaiq, M. D., Cheema, M. D. A., Kamal, A.: Transformer based urdu handwritten text optical character reader, arXiv preprint arXiv:2206.04575. (2022)."},{"issue":"4","key":"544_CR20","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10032-022-00416-5","volume":"25","author":"N Riaz","year":"2022","unstructured":"Riaz, N., Arbab, H., Maqsood, A., Nasir, K., Ul-Hasan, A., Shafait, F.: Conv-transformer architecture for unconstrained off-line urdu handwriting recognition. Int. J. Doc. Anal. Recogn. (IJDAR) 25(4), 373\u2013384 (2022)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"issue":"13\u201315","key":"544_CR21","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1016\/j.neucom.2007.12.036","volume":"71","author":"AM Schaefer","year":"2008","unstructured":"Schaefer, A.M., et al.: Learning long-term dependencies with recurrent neural networks. Neurocomputing 71(13\u201315), 2481\u20132488 (2008). https:\/\/doi.org\/10.1016\/j.neucom.2007.12.036","journal-title":"Neurocomputing"},{"key":"544_CR22","unstructured":"Dosovitskiy, A. et al.: An image is worth 16\u00d716 words: transformers for image recognition at scale,arXiv preprint arXiv:2010.11929, (2022)"},{"key":"544_CR23","doi-asserted-by":"publisher","unstructured":"Limitation of VITs Zheng, S. et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 6877\u20136886 (2021), https:\/\/doi.org\/10.1109\/CVPR46437.2021.00681.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"544_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows, arXiv:2103.14030, (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"544_CR25","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1007\/s00371-023-02939-2","volume":"40","author":"D Yao","year":"2024","unstructured":"Yao, D., Shao, Y.: A data efficient transformer based on Swin Transformer. Vis. Comput. 40, 2589\u201398 (2024)","journal-title":"Vis. Comput."},{"key":"544_CR26","doi-asserted-by":"publisher","unstructured":"Maqsood, A., Riaz, N., Ul-Hasan, A., Shafait, F.: A unified architecture for Urdu printed and handwritten text recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document analysis and recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14190. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-41685-9_8 (2023)","DOI":"10.1007\/978-3-031-41685-9_8"},{"key":"544_CR27","doi-asserted-by":"publisher","DOI":"10.21227\/437M-MK79","author":"DAFG Ganai","year":"2024","unstructured":"Ganai, D.A.F.G.: Urdu handwritten ligature dataset. IEEE DataPort (2024). https:\/\/doi.org\/10.21227\/437M-MK79","journal-title":"IEEE DataPort"},{"issue":"2","key":"544_CR28","first-page":"1","volume":"5","author":"YK Singh","year":"2016","unstructured":"Singh, Y. K.: Finding connected components in a gray scale image. ADBU J. Eng. Technol. 5(2), 1\u20134, (2016).","journal-title":"ADBU J. Eng. Technol"},{"key":"544_CR29","unstructured":"Vaswani, A. et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)."},{"key":"544_CR30","unstructured":"Hendricks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv, Available at: arXiv:1606.08415, (2016)"},{"issue":"6","key":"544_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., et al.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"key":"544_CR32","doi-asserted-by":"publisher","unstructured":"Szegedy, C. et al.: Going deeper with convolutions. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594. (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"544_CR33","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2016.415","author":"H Ramchoun","year":"2016","unstructured":"Ramchoun, H., et al.: Multilayer perceptron: architecture optimization and training. IJIMAI (2016). https:\/\/doi.org\/10.9781\/ijimai.2016.415","journal-title":"IJIMAI"},{"key":"544_CR34","first-page":"467","volume":"1391","author":"AK Reyes","year":"2015","unstructured":"Reyes, A.K., et al.: Fine-tuning deep convolutional networks for plant recognition. CLEF 1391, 467\u2013475 (2015)","journal-title":"CLEF"},{"key":"544_CR35","doi-asserted-by":"publisher","first-page":"124945","DOI":"10.1109\/ACCESS.2021.3110787","volume":"9","author":"T Nasir","year":"2021","unstructured":"Nasir, T., Malik, M.K., Shahzad, K.: MMU-OCR-21: towards end-to-end urdu text recognition using deep learning. IEEE Access 9, 124945\u2013124962 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3110787","journal-title":"IEEE Access"},{"issue":"3","key":"544_CR36","first-page":"2767","volume":"12","author":"SM Ahmed","year":"2024","unstructured":"Ahmed, S.M.: Leveraging the swin transformer for enhanced handwritten Urdu character and digit recognition. Int. J. Intell. Syst. Appl. Eng. 12(3), 2767\u20132776 (2024)","journal-title":"Int. J. Intell. Syst. Appl. Eng."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00544-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-025-00544-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00544-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T06:49:44Z","timestamp":1775803784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-025-00544-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["544"],"URL":"https:\/\/doi.org\/10.1007\/s10032-025-00544-8","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,12]]},"assertion":[{"value":"8 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}