{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:58:36Z","timestamp":1782316716567,"version":"3.54.5"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T00:00:00Z","timestamp":1679702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2023,4,30]]},"abstract":"<jats:p>\n            The Devanagari script is one of the most widely used scripts worldwide. The existing deep learning-based optical character recognition system for printed Devanagari scripts using\n            <jats:bold>Convolutional Neural Network \u2013 Recurrent Neural Network<\/jats:bold>\n            , or\n            <jats:bold>CRNN<\/jats:bold>\n            is not robust enough to recognize any randomly printed Devanagari scanned document. At present, the hyper-parameters of the CRNN system are selected randomly either with the trial-and-error or grid search methods. Moreover, there is no optimized way to choose the hyper-parameters of the CRNN, which improves the recognition accuracy for Devanagari documents. Furthermore, the lack of standard Devanagari script datasets has hampered the development of word recognizers. In this paper, the hyper-parameter of the CRNN system is optimized using Taguchi's method of optimization. The performance of the hyper-parameters optimized CRNN system is compared with the current state-of-the-art text recognition CRNN network. The results reveal that the CRNN optimized with Taguchi's method performs better than the CRNN-based systems.\n          <\/jats:p>","DOI":"10.1145\/3578549","type":"journal-article","created":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T13:24:07Z","timestamp":1674134647000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-3933","authenticated-orcid":false,"given":"Shaheera Saba Mohd Naseem","family":"Akhter","sequence":"first","affiliation":[{"name":"College of Engineering, Pune, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0584-5208","authenticated-orcid":false,"given":"Priti P.","family":"Rege","sequence":"additional","affiliation":[{"name":"College of Engineering, Pune, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,25]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Don Vaughan. The World's 5 Most Commonly Used Writing Systems. https:\/\/www.britannica.com\/list\/the-worlds-5-most-commonly-used-writing-systems."},{"key":"e_1_3_1_3_2","first-page":"653","volume-title":"Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR","author":"Bansal V.","year":"1999","unstructured":"V. Bansal and R. M. K. Sinha. 1999. Partitioning and searching dictionary for correction of optically read Devanagari character strings. In Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR. 653\u2013656."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/3468.852443"},{"key":"e_1_3_1_5_2","first-page":"946","volume-title":"13th International Conference on Document Analysis and Recognition (ICDAR)","author":"Karayil T.","year":"2015","unstructured":"T. Karayil, A. Ul-Hasan, and T. M. Breuel. 2015. A segmentation-free approach for printed Devanagari script recognition. In 13th International Conference on Document Analysis and Recognition (ICDAR). IEEE, 946\u2013950."},{"key":"e_1_3_1_6_2","first-page":"1","volume-title":"Fourth International Conference on Image Information Processing (ICIIP)","author":"Chavan V.","year":"2017","unstructured":"V. Chavan, A. Malage, K. Mehrotra, and M. K. Gupta. 2017. Printed text recognition using BLSTM and MDLSTM for Indian languages. In Fourth International Conference on Image Information Processing (ICIIP). 1\u20136."},{"key":"e_1_3_1_7_2","first-page":"322","volume-title":"Proceedings of the 21st International Conference on Pattern Recognition (ICPR\u201912)","author":"Sankaran N.","year":"2012","unstructured":"N. Sankaran and C. V. Jawahar. 2012. Recognition of printed Devanagari text using BLSTM neural network. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR\u201912). 322\u2013325."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_1_10_2","first-page":"31","article-title":"Connectionist temporal classification with maximum entropy regularization","author":"Liu H.","year":"2018","unstructured":"H. Liu, S. Jin, and C. Zhang. 2018. Connectionist temporal classification with maximum entropy regularization. Advances in Neural Information Processing Systems (2018), 31.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_11_2","first-page":"42","volume-title":"14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","author":"Mathew M.","year":"2017","unstructured":"M. Mathew, J. Mohit, and C. V. Jawahar. 2017. Benchmarking scene text recognition in Devanagari, Telugu, and Malayalam. In 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE, 42\u201346."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2574840"},{"key":"e_1_3_1_13_2","first-page":"163","article-title":"A feature-based scheme for the machine recognition of printed Devanagari script","author":"Palit S.","year":"1995","unstructured":"S. Palit, B. B. Chaudhuri, P. P. Das, and B. N. Chatterjee. 1995. A feature-based scheme for the machine recognition of printed Devanagari script. In Pattern Recognition, Image Processing, and Computer Vision (1995), 163\u2013168.","journal-title":"Pattern Recognition, Image Processing, and Computer Vision"},{"key":"e_1_3_1_14_2","first-page":"12","article-title":"Printed devanagari script OCR system","volume":"10","author":"Pal U.","year":"1997","unstructured":"U. Pal and B. Chaudhuri. 1997. Printed devanagari script OCR system. Vivek-Bombay-. 10 (1997), 12\u201324.","journal-title":"Vivek-Bombay-"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.02.003"},{"key":"e_1_3_1_16_2","first-page":"23","volume-title":"International Conference on Information Technology, (ICIT'08)","author":"Shaw B.","year":"2008","unstructured":"B. Shaw, S. Kumar Parui, and M. Shridhar. 2008. Online handwritten Devanagari word recognition: A holistic approach based on directional chain code feature and HMM. In International Conference on Information Technology, (ICIT'08). IEEE, 23\u2013208."},{"key":"e_1_3_1_17_2","volume-title":"Proceedings of Sixth International Conference on Document Analysis and Recognition","author":"Bansal V.","year":"2001","unstructured":"V. Bansal and R. M. K. Sinha. 2001. A complete OCR for printed Hindi text in Devanagari script. Proceedings of Sixth International Conference on Document Analysis and Recognition. IEEE Computer Society."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.807272"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_3_1_21_2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, I. Sutskever, and G. E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS). 1097\u20131105.","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-021-01664-7"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-020-00350-4"},{"key":"e_1_3_1_24_2","first-page":"252","volume-title":"Fifth International Conference on Image Information Processing (ICIIP)","author":"Mehrotra K.","year":"2019","unstructured":"K. Mehrotra, M. K. Gupta, and K. Khajuria. 2019. Collaborative deep neural network for printed text recognition of Indian languages. In Fifth International Conference on Image Information Processing (ICIIP). 252\u2013256."},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/978-3-030-36808-1_31","volume-title":"Proceedings of the International Conference on Neural Information Processing","author":"Zhang X.","year":"2019","unstructured":"X. Zhang, X. Chen, L. Yao, C. Ge, and M. Dong. 2019. Deep neural network hyper-parameter optimization with orthogonal array tuning. In Proceedings of the International Conference on Neural Information Processing. Cham: Springer, 287\u2013295."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2834892.2834896"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298360"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242042"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","unstructured":"G. Taguchi and M. S. Phadke. 1989. Quality engineering through design optimization. In Quality Control Robust Design and the Taguchi Method . Boston MA: Springer 77\u201396.","DOI":"10.1007\/978-1-4684-1472-1_5"},{"key":"e_1_3_1_31_2","unstructured":"G. Taguchi and Y. Yokoyama. 1993. Taguchi Methods: Design of Experiments . Taguchi Methods Series 4."},{"key":"e_1_3_1_32_2","unstructured":"T. P. Bagchi. 1993. Taguchi Methods Explained: Practical Steps to Robust Design . Hoboken: Prentice-Hall."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_1_34_2","first-page":"448","volume-title":"International Conference on Machine Learning.","author":"Ioffe S.","year":"2015","unstructured":"S. Ioffe and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448\u2013456."},{"key":"e_1_3_1_35_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Joseph R.","year":"2016","unstructured":"R. Joseph et al. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_1_36_2","volume-title":"arXiv preprint","author":"Kingma D. P.","year":"2014","unstructured":"D. P. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"e_1_3_1_37_2","volume-title":"arXiv preprint","author":"Nwankpa C.","year":"2018","unstructured":"C. Nwankpa, W. Ijomah, A. Gachagan, and S. Marshall. 2018. Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36808-1_31"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.18494\/SAM.2021.3015"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4047915"},{"key":"e_1_3_1_43_2","first-page":"182","volume-title":"International Conference on Document Analysis and Recognition","author":"Gunna S.","year":"2021","unstructured":"S. Gunna, R. Saluja, and C. V. Jawahar. 2021. Transfer learning for scene text recognition in Indian languages. In International Conference on Document Analysis and Recognition, Springer, Cham, 182\u2013197."}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578549","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:37Z","timestamp":1750183717000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,25]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4,30]]}},"alternative-id":["10.1145\/3578549"],"URL":"https:\/\/doi.org\/10.1145\/3578549","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,25]]},"assertion":[{"value":"2022-06-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}