{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T11:19:21Z","timestamp":1790939961180,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,5,21]],"date-time":"2020-05-21T00:00:00Z","timestamp":1590019200000},"content-version":"vor","delay-in-days":20,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2020,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Kuzushiji, a cursive writing style, had been used in Japan for over a thousand years starting from the eighth century. Over 3 million books on a diverse array of topics, such as literature, science, mathematics and even cooking are preserved. However, following a change to the Japanese writing system in 1900, Kuzushiji has not been included in regular school curricula. Therefore, most Japanese natives nowadays cannot read books written or printed just 150 years ago. Museums and libraries have invested a great deal of effort into creating digital copies of these historical documents as a safeguard against fires, earthquakes and tsunamis. The result has been datasets with hundreds of millions of photographs of historical documents which can only be read by a small number of specially trained experts. Thus there has been a great deal of interest in using machine learning to automatically recognize these historical texts and transcribe them into modern Japanese characters. Our proposed model KuroNet (which builds on Clanuwat et al. in International conference on document analysis and recognition (ICDAR), 2019) outperforms other model for Kuzushiji recognition. In this paper, KuroNet achieves higher accuracy while still recognizing entire pages of text using the residual U-Net architecture from adding more regularization. We also explore areas where our system is limited and suggests directions for future work.<\/jats:p>","DOI":"10.1007\/s42979-020-00186-z","type":"journal-article","created":{"date-parts":[[2020,5,21]],"date-time":"2020-05-21T15:03:32Z","timestamp":1590073412000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["KuroNet: Regularized Residual U-Nets for End-to-End Kuzushiji Character Recognition"],"prefix":"10.1007","volume":"1","author":[{"given":"Alex","family":"Lamb","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarin","family":"Clanuwat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asanobu","family":"Kitamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,5,21]]},"reference":[{"key":"186_CR1","unstructured":"Beckham C, Honari S, Verma V, Lamb AM, Ghadiri F, Hjelm RD, Bengio Y, Pal C. On adversarial mixup resynthesis. In: Advances in neural information processing systems. 2019. p. 4348\u20134359."},{"key":"186_CR2","doi-asserted-by":"publisher","unstructured":"Bezerra BLD, Zanchettin C, de\u00a0Andrade VB. A hybrid RNN model for cursive offline handwriting recognition. In: Brazilian symposium on neural networks. 2012. p. 113\u2013118. https:\/\/doi.org\/10.1109\/SBRN.2012.41.","DOI":"10.1109\/SBRN.2012.41"},{"key":"186_CR3","unstructured":"Chen J, Gu, Q. Closing the generalization gap of adaptive gradient methods in training deep neural networks. arXiv preprint arXiv:1806.06763 (2018)."},{"key":"186_CR4","unstructured":"Clanuwat T, Bober-Irizar M, Kitamoto A, Lamb A, Yamamoto, K, Ha D. Deep learning for classical Japanese literature. Neural information processing systems (Neurips) creativity workshop. http:\/\/arxiv.org\/abs\/1812.01718 (2018)."},{"key":"186_CR5","doi-asserted-by":"crossref","unstructured":"Clanuwat T, Lamb A, Kitamoto A. End-to-end pre-modern Japanese character (kuzushiji) spotting with deep learning. In: Proceeding of information processing society of Japan, Jinmoncom. 2018.","DOI":"10.1109\/ICDAR.2019.00103"},{"key":"186_CR6","doi-asserted-by":"crossref","unstructured":"Clanuwat T, Lamb A, Kitamoto A. Kuronet: Pre-modern Japanese kuzushiji character recognition with deep learning. In: International conference on document analysis and recognition (ICDAR). 2019.","DOI":"10.1109\/ICDAR.2019.00103"},{"key":"186_CR7","unstructured":"Dumoulin V, Belghazi I, Poole B, Mastropietro O, Lamb A, Arjovsky M, Courville A. Adversarially learned inference. 2016."},{"key":"186_CR8","unstructured":"Ester M, Kriegel HP, Sander J, Xu X, et\u00a0al. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceeding of Association for the advancement of artificial intelligence (AAAI). 1996."},{"key":"186_CR9","unstructured":"Goyal A, Ke NR, Lamb A, Hjelm RD, Pal C, Pineau J, Bengio Y. Actual: Actor-critic under adversarial learning. arXiv preprint arXiv:1711.04755 (2017)."},{"key":"186_CR10","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)."},{"key":"186_CR11","unstructured":"Iwanamishoten: the general catalog of national books. Iwanamishoten. 1963."},{"key":"186_CR12","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"186_CR13","unstructured":"Lamb AM, GOYAL AGAP, Zhang Y, Zhang S, Courville AC, Bengio Y. Professor forcing: a new algorithm for training recurrent networks. In: Advances in neural information processing systems. 2016. p. 4601\u20134609."},{"key":"186_CR14","unstructured":"Le\u00a0Duc A, Mochihashi D, Masuda K, Mima H. An attention-based encoder-decoder for recognizing Japanese historical documents. In: Pattern recognition and machine understanding (PRMU). https:\/\/www.ieice.org\/ken\/paper\/20181213H1IM\/eng\/ (2018)."},{"key":"186_CR15","unstructured":"LeCun Y. The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ (1998)."},{"key":"186_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen HT, Ly NT, Nguyen KC, Nguyen CT, Nakagawa M. Attempts to recognize anomalously deformed kana in japanese historical documents. In: Proceedings of the 4th international workshop on historical document imaging and processing. ACM; 2017. p. 31\u201336.","DOI":"10.1145\/3151509.3151514"},{"key":"186_CR17","unstructured":"Quan TM, Hildebrand DGC, Jeong W. Fusionnet: a deep fully residual convolutional neural network for image segmentation in connectomics. CoRR abs\/1612.05360. http:\/\/arxiv.org\/abs\/1612.05360 (2016)."},{"key":"186_CR18","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer; 2015. p. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"186_CR19","unstructured":"Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T. One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065 (2016)."},{"issue":"3","key":"186_CR20","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/0031-3203(73)90044-7","volume":"5","author":"KM Sayre","year":"1973","unstructured":"Sayre KM. Machine recognition of handwritten words: a project report. Pattern Recognit. 1973;5(3):213\u201328. https:\/\/doi.org\/10.1016\/0031-3203(73)90044-7.","journal-title":"Pattern Recognit"},{"key":"186_CR21","unstructured":"Takashiro K. Syllabary seen in the textbook of the meiji first year. The bulletin of Jissen Women\u2019s Junior College. Jissen Joshi Tankidaigaku Kiyou. 2013. p. 109\u2013119."},{"key":"186_CR22","unstructured":"Tarvainen A, Valpola H. Weight-averaged consistency targets improve semi-supervised deep learning results. CoRR abs\/1703.01780. http:\/\/arxiv.org\/abs\/1703.01780 (2017)."},{"key":"186_CR23","unstructured":"Verma V, Lamb A, Beckham C, Najafi A, Courville A, Mitliagkas I, Bengio Y. Manifold mixup: learning better representations by interpolating hidden states. 2019."},{"key":"186_CR24","doi-asserted-by":"crossref","unstructured":"Verma V, Lamb A, Kannala J, Bengio Y, Lopez-Paz D. Interpolation consistency training for semi-supervised learning. In: International joint conference on artificial intelligence (IJCAI). arXiv:1903.03825 (2019).","DOI":"10.24963\/ijcai.2019\/504"},{"key":"186_CR25","unstructured":"Wilson AC, Roelofs R, Stern M, Srebro N, Recht B. The marginal value of adaptive gradient methods in machine learning. In: Advances in neural information processing systems. 2017. p. 4148\u20134158."},{"key":"186_CR26","unstructured":"Wu Y, He K. Group normalization. arXiv preprint arXiv:1803.08494 (2018)."},{"key":"186_CR27","unstructured":"Yaz\u0131c\u0131 Y, Foo CS, Winkler S, Yap KH, Piliouras G, Chandrasekhar V. The unusual effectiveness of averaging in gan training. arXiv preprint arXiv:1806.04498 (2018)."},{"key":"186_CR28","unstructured":"Yaz\u0131c\u0131 Y, Foo CS, Winkler S, Yap KH, Piliouras G, Chandrasekhar V. The unusual effectiveness of averaging in GAN training. In: International conference on learning representations. 2019."},{"key":"186_CR29","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00186-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-020-00186-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00186-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T23:11:37Z","timestamp":1621552297000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-020-00186-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["186"],"URL":"https:\/\/doi.org\/10.1007\/s42979-020-00186-z","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"value":"2662-995X","type":"print"},{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]},"assertion":[{"value":"30 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"177"}}