{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:12:57Z","timestamp":1769184777392,"version":"3.49.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Optical character recognition (OCR) has proved a powerful tool for the digital analysis of printed historical documents. However, its ability to localize and identify individual glyphs is challenged by the tremendous variety in historical type design, the physicality of the printing process, and the state of conservation. We propose to mitigate these problems by a downstream fine-tuning step that corrects for pathological and undesirable extraction results. We implement this idea by using a joint energy-based model which classifies individual glyphs and simultaneously prunes potential out-of-distribution (OOD) samples like rubrications, initials, or ligatures. During model training, we introduce specific margins in the energy spectrum that aid this separation and explore the glyph distribution\u2019s typical set to stabilize the optimization procedure. We observe strong classification at 0.972 AUPRC across 42 lower- and uppercase glyph types on a challenging digital reproduction of Johannes Balbus\u2019 <jats:italic>Catholicon<\/jats:italic>, matching the performance of purely discriminative methods. At the same time, we achieve OOD detection rates of 0.989 AUPRC and 0.946 AUPRC for OOD \u2018clutter\u2019 and \u2018ligatures\u2019 which substantially improves upon recently proposed OOD detection techniques. The proposed approach can be easily integrated into the postprocessing phase of current OCR to aid reproduction and shape analysis research.<\/jats:p>","DOI":"10.1007\/s10032-023-00442-x","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T10:14:52Z","timestamp":1687428892000},"page":"223-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Classification of incunable glyphs and out-of-distribution detection with joint energy-based models"],"prefix":"10.1007","volume":"26","author":[{"given":"Florian","family":"Kordon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaus","family":"Weichselbaumer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randall","family":"Herz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Mossman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Potten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Seuret","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Mayr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,22]]},"reference":[{"issue":"1","key":"442_CR1","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1207\/s15516709cog0901_7","volume":"9","author":"DH Ackley","year":"1985","unstructured":"Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A learning algorithm for Boltzmann machines. Cogn. Sci. 9(1), 147\u2013169 (1985)","journal-title":"Cogn. Sci."},{"key":"442_CR2","unstructured":"Arbel, M., Zhou, L., Gretton, A.: Generalized energy based models. arXiv preprint arXiv:2003.05033 (2020)"},{"key":"442_CR3","unstructured":"Betancourt, M.: A conceptual introduction to Hamiltonian Monte Carlo. arXiv preprint arXiv:1701.02434 (2017)"},{"issue":"11","key":"442_CR4","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/TPAMI.2021.3116668","volume":"44","author":"S Bond-Taylor","year":"2022","unstructured":"Bond-Taylor, S., Leach, A., Long, Y., Willcocks, C.G.: Deep generative modelling: a comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7327\u20137347 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3116668","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"442_CR5","unstructured":"Brosse, N., Moulines, E., Durmus, A.: The promises and pitfalls of stochastic gradient Langevin dynamics. In: Advances in Neural Information Processing Systems. NIPS\u201918, pp. 8278\u20138288. Curran Associates Inc., Montr\u00e9al (2018)"},{"key":"442_CR6","doi-asserted-by":"crossref","unstructured":"Budig, B., van Dijk, T.C., Kirchner, F.: Glyph miner: a system for efficiently extracting glyphs from early prints in the context of OCR. In: Joint Conference on Digital Libraries, pp. 31\u201334 (2016)","DOI":"10.1145\/2910896.2910915"},{"key":"442_CR7","volume-title":"Extracting Spatial Information from Historical Maps: Algorithms and Interaction","author":"B Budig","year":"2018","unstructured":"Budig, B.: Extracting Spatial Information from Historical Maps: Algorithms and Interaction. W\u00fcrzburg University Press, W\u00fcrzburg (2018)"},{"key":"442_CR8","doi-asserted-by":"publisher","unstructured":"B\u00fcttner, J., Martinetz, J., El-Hajj, H., Valleriani, M.: CorDeep and the Sacrobosco dataset: detection of visual elements in historical documents. J. Imaging 8(10), 285. https:\/\/doi.org\/10.3390\/jimaging8100285","DOI":"10.3390\/jimaging8100285"},{"key":"442_CR9","doi-asserted-by":"crossref","unstructured":"Caluori, U., Simon, K.: Glyph recognition by pattern matching with on-the-fly generated patterns. In: International Conference on Software, Telecommunications and Computer Networks, pp. 1\u20135 (2013)","DOI":"10.1109\/SoftCOM.2013.6671876"},{"key":"442_CR10","unstructured":"Carreira-Perpi\u00f1\u00e1n, M.A., Hinton, G.: On contrastive divergence learning. In Cowell, R.G., Ghahramani, Z. (eds.) International Workshop on Artificial Intelligence and Statistics, Volume\u00a0R5 of Proceedings of Machine Learning Research, pp. 33\u201340. PMLR (2005)"},{"key":"442_CR11","unstructured":"Che, T., Zhang, R., Sohl-Dickstein, J., Larochelle, H., Paull, L., Cao, Y., Bengio, Y.: Your GAN is secretly an energy-based model and you should use discriminator driven latent sampling. In: International Conference on Neural Information Processing Systems, NIPS\u201920, Red Hook, NY, USA. Curran Associates Inc (2020)"},{"key":"442_CR12","unstructured":"Choi, H., Jang, E., Alemi, A.A.: Waic, but why? Generative ensembles for robust anomaly detection. arXiv preprint arXiv:1810.01392 (2018)"},{"key":"442_CR13","doi-asserted-by":"crossref","unstructured":"Coustaty, M., Ogier, J.M.: Graph matching versus bag of graph: a comparative study for lettrines recognition. In: International Conference on Document Analysis and Recognition, pp. 356\u2013360 (2015)","DOI":"10.1109\/ICDAR.2015.7333783"},{"key":"442_CR14","unstructured":"Dalitz, C., Pranzas, C.: German lute tablature recognition. In: International Conference on Learning Representations (2021)"},{"key":"442_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. Int. Confer. Learn. Represent. (2021)"},{"key":"442_CR16","unstructured":"Du, Y., Li, S., Mordatch, I.: Compositional visual generation with energy based models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 6637\u20136647. Curran Associates Inc (2020)"},{"key":"442_CR17","unstructured":"Du, Y., Li, S., Sharma, Y., Tenenbaum, B.J., Mordatch, I.: Unsupervised learning of compositional energy concepts. In: Advances in Neural Information Processing Systems (2021)"},{"key":"442_CR18","unstructured":"Du, Y., Li, S., Tenenbaum, J., Mordatch, I.: Learning iterative reasoning through energy minimization. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.), International Conference on Machine Learning, Volume 162 of Proceedings of Machine Learning Research, pp. 5570\u20135582. PMLR (2022)"},{"key":"442_CR19","unstructured":"Du, Y., Li, S., Tenenbaum, B.J., Mordatch, I.: Improved contrastive divergence training of energy based models. In: Meila, M., Zhang, T. (eds.) International Conference on Machine Learning, vol. 139, pp. 2837\u20132848. PMLR, 18\u201324 July 2021 (2021)"},{"key":"442_CR20","unstructured":"Du, Y., Mordatch, I.: Implicit generation and modeling with energy based models. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc (2019)"},{"key":"442_CR21","doi-asserted-by":"crossref","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., Romanello, M., Douvet, A.: A survey of named entity recognition and classification on historical documents. arXiv:2109.11406 (2022) (to appear) in ACM J. Comput., Surv","DOI":"10.1145\/3604931"},{"key":"442_CR22","unstructured":"Elflein, S., Charpentier, B., Z\u00fcgner, D., G\u00fcnnemann, S.: On out-of-distribution detection with energy-based models. In: Uncertainty and Robustness in Deep Learning Workshop (UDL\u2014ICML) (2021)"},{"key":"442_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018). https:\/\/doi.org\/10.1016\/j.neunet.2017.12.012","journal-title":"Neural Netw."},{"key":"442_CR24","unstructured":"Gesamtkatalog der Wiegendrucke: Incunable GW03182. https:\/\/www.gesamtkatalogderwiegendrucke.de\/docs\/GW03182.htm. Accessed 25 Oct 2022"},{"key":"442_CR25","unstructured":"GlyphCollector. https:\/\/glyphcollector.app. Accessed 13 Nov 2022"},{"key":"442_CR26","doi-asserted-by":"crossref","unstructured":"Goyal, K., Dyer, C., Warren, C., G\u2019Sell, M., Berg-Kirkpatrick, T.: A probabilistic generative model for typographical analysis of early modern printing. In: Annual Meeting of the Association for Computational Linguistics, Online, pp. 2954\u20132960. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.266"},{"key":"442_CR27","unstructured":"Grathwohl, W.S., Kelly, J.J., Hashemi, M., Norouzi, M., Swersky, K., Duvenaud, D.: No MCMC for me: Amortized sampling for fast and stable training of energy-based models. In: International Conference on Learning Representations (2021)"},{"key":"442_CR28","unstructured":"Grathwohl, W., Wang, K.-C., Jacobsen, J.-H., Duvenaud, D., Norouzi, M., Swersky, K.: Your classifier is secretly an energy based model and you should treat it like one. In: International Conference on Learning Representations (2020)"},{"key":"442_CR29","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, ICML\u201917, pp. 1321-1330. JMLR.org (2017)"},{"key":"442_CR30","doi-asserted-by":"crossref","unstructured":"Hein, M., Andriushchenko, M., Bitterwolf, J.: Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 41\u201350 (2019)","DOI":"10.1109\/CVPR.2019.00013"},{"key":"442_CR31","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations (2017)"},{"key":"442_CR32","doi-asserted-by":"crossref","unstructured":"Hintersdorf, D., Struppek, L., Kersting, K.: To trust or not to trust prediction scores for membership inference attacks. In: International Joint Conference on Artificial Intelligence (2022)","DOI":"10.24963\/ijcai.2022\/422"},{"key":"442_CR33","doi-asserted-by":"crossref","unstructured":"Hinton, G.: Products of experts. In: International Conference on Artificial Neural Networks, vol.\u00a01, pp. 1\u20136 (1999)","DOI":"10.1049\/cp:19991075"},{"issue":"8","key":"442_CR34","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771\u20131800 (2002)","journal-title":"Neural Comput."},{"issue":"8","key":"442_CR35","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","volume":"79","author":"JJ Hopfield","year":"1982","unstructured":"Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79(8), 2554\u20132558 (1982)","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"442_CR36","first-page":"677","volume":"34","author":"R Huang","year":"2021","unstructured":"Huang, R., Geng, A., Li, Y.: On the importance of gradients for detecting distributional shifts in the wild. Adv. Neural. Inf. Process. Syst. 34, 677\u2013689 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"442_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42484-021-00057-7","volume":"4","author":"P Huembeli","year":"2022","unstructured":"Huembeli, P., Arrazola, J.M., Killoran, N., Mohseni, M., Wittek, P.: The physics of energy-based models. Quantum Mach. Intell. 4(1), 1\u201313 (2022)","journal-title":"Quantum Mach. Intell."},{"key":"442_CR38","unstructured":"Incunabula Short Title Catalogue: ib00020000. https:\/\/data.cerl.org\/istc\/ib00020000. Accessed 25 Oct 2022"},{"key":"442_CR39","doi-asserted-by":"crossref","unstructured":"Koch, T., Liebezeit, F., Rie\u00df, C., Christlein, V., K\u00f6hler, T.: Exploring the open world using incremental extreme value machines. In: International Conference on Pattern Recognition, Pattern Recognition (2022)","DOI":"10.1109\/ICPR56361.2022.9956423"},{"issue":"2","key":"442_CR40","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10032-013-0209-0","volume":"17","author":"G Lazzara","year":"2014","unstructured":"Lazzara, G., G\u00e9raud, T.: Efficient multiscale Sauvola\u2019s binarization. Int. J. Doc. Anal. Recogn. 17(2), 105\u2013123 (2014). https:\/\/doi.org\/10.1007\/s10032-013-0209-0","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"442_CR41","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.J.: A tutorial on energy-based learning. In: Bakir, G., Hofman, T., Scholkopt, B., Smola, A. , Taskar, B. (eds.) Predicting Structured Data. MIT Press (2006)","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"442_CR42","unstructured":"Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: International Conference on Neural Information Processing Systems, NIPS\u201918, Red Hook, NY, USA, pp. 7167\u20137177. Curran Associates Inc (2018)"},{"key":"442_CR43","unstructured":"Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: International Conference on Learning Representations (2017)"},{"key":"442_CR44","unstructured":"Li, S., Du, Y., van\u00a0de Ven, G.M., Mordatch, I.: Energy-based models for continual learning. arXiv preprint arXiv:2011.12216 (2020)"},{"key":"442_CR45","unstructured":"Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations (2018)"},{"key":"442_CR46","unstructured":"Liu, W., Wang, X., Owens, J.D., Li, Y.: Energy-based out-of-distribution detection. In: International Conference on Neural Information Processing Systems, NIPS\u201920, Red Hook, NY, USA. Curran Associates Inc (2020)"},{"key":"442_CR47","unstructured":"Meinke, A., Hein, M.: Towards neural networks that provably know when they don\u2019t know. In: International Conference on Learning Representations (2020)"},{"key":"442_CR48","doi-asserted-by":"crossref","unstructured":"Meyer-Lerbs, L., Schuldt, A., Gottfried, B.: Glyph extraction from historic document images. In: ACM Symposium on Document Engineering, DocEng \u201910, New York, NY, USA, pp. 227-230. Association for Computing Machinery (2010)","DOI":"10.1145\/1860559.1860609"},{"key":"442_CR49","unstructured":"Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., Lakshminarayanan, B.: Hybrid models with deep and invertible features. In: Chaudhuri, K., Salakhutdinov, R. (eds.) International Conference on Machine Learning, Volume\u00a097 of Proceedings of Machine Learning Research, pp. 4723\u20134732. PMLR (2019)"},{"key":"442_CR50","unstructured":"Nalisnick, E., Matsukawa, A., Teh, Y.W., Lakshminarayanan, B.: Detecting out-of-distribution inputs to deep generative models using typicality. arXiv:1906.02994 (2019)"},{"key":"442_CR51","doi-asserted-by":"crossref","unstructured":"Neudecker, C., Baierer, K., Federbusch, M., Boenig, M., W\u00fcrzner, K.M., Hartmann, V., Herrmann, E.: OCR-D: an end-to-end open source OCR framework for historical printed documents. In: International Conference on Digital Access to Textual Cultural Heritage, DATeCH2019, New York, NY, USA, pp. 53-58. Association for Computing Machinery (2019)","DOI":"10.1145\/3322905.3322917"},{"key":"442_CR52","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 427\u2013436 (2015)","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"442_CR53","unstructured":"Nijkamp, E., Hill, M., Zhu, S.C., Wu, Y.N.: Learning non-convergent non-persistent short-run MCMC toward energy-based model. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"442_CR54","doi-asserted-by":"crossref","unstructured":"Nijkamp, E., Hill, M., Han, T., Zhu, S.C., Wu, Y.N.: On the anatomy of MCMC-based maximum likelihood learning of energy-based models. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 5272\u20135280 (2020)","DOI":"10.1609\/aaai.v34i04.5973"},{"key":"442_CR55","unstructured":"Osogami, T.: Boltzmann machines and energy-based models. arXiv preprint arXiv:1708.06008 (2017)"},{"issue":"57","key":"442_CR56","first-page":"1","volume":"22","author":"G Papamakarios","year":"2021","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. J. Mach. Learn. Res. 22(57), 1\u201364 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"442_CR57","doi-asserted-by":"publisher","unstructured":"Reul, C., Christ, D., Hartelt, A., Balbach, N., Wehner, M., Springmann, U., Wick, C., Grundig, C., B\u00fcttner, A., Puppe, F.: OCR4all\u2014An open-source tool providing a (semi-)automatic OCR workflow for historical printings. Appl. Sci. 9(22), 4853 (2019). https:\/\/doi.org\/10.3390\/app9224853","DOI":"10.3390\/app9224853"},{"key":"442_CR58","doi-asserted-by":"publisher","unstructured":"Sauvola, J., Pietik\u00e4inen, M.: Adaptive document image binarization. Pattern Recogn. 33(2), 225\u2013236 (2000). https:\/\/doi.org\/10.1016\/S0031-3203(99)00055-2","DOI":"10.1016\/S0031-3203(99)00055-2"},{"key":"442_CR59","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the Tesseract OCR engine. In: International Conference on Document Analysis and Recognition, vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"442_CR60","unstructured":"Song, Y., Kingma, D.P.: How to train your energy-based models. arXiv preprint arXiv:2101.03288 (2021)"},{"key":"442_CR61","doi-asserted-by":"crossref","unstructured":"Souibgui, M.A., Forn\u00e9s, A., Kessentini, Y., Tudor, C.: A few-shot learning approach for historical ciphered manuscript recognition. In: International Conference on Pattern Recognition, pp. 5413\u20135420. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413255"},{"issue":"1","key":"442_CR62","doi-asserted-by":"publisher","first-page":"97","DOI":"10.21248\/jlcl.33.2018.220","volume":"33","author":"U Springmann","year":"2018","unstructured":"Springmann, U., Reul, C., Dipper, S., Baiter, J.: Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin. J. Lang. Technol. Comput. Linguist. 33(1), 97\u2013114 (2018)","journal-title":"J. Lang. Technol. Comput. Linguist."},{"key":"442_CR63","unstructured":"Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: International Conference on Machine Learning, pp. 20827\u201320840. PMLR (2022)"},{"key":"442_CR64","unstructured":"Tesseract 4.00. https:\/\/tesseract-ocr.github.io\/tessdoc\/tess4\/TrainingTesseract-4.00.html. Accessed 12 Nov 2022"},{"key":"442_CR65","doi-asserted-by":"crossref","unstructured":"Tonin, F., Pandey, A., Patrinos, P., Suykens, J.A.K.: Unsupervised energy-based out-of-distribution detection using Stiefel-restricted kernel machine. In: International Joint Conference on Neural Networks, pp. 1\u20138 (2021)","DOI":"10.1109\/IJCNN52387.2021.9533706"},{"key":"442_CR66","unstructured":"Type 1:82G bei Drucker des Catholicon (GW 3182). https:\/\/tw.staatsbibliothek-berlin.de\/ma06249. Accessed 25 Oct 2022"},{"key":"442_CR67","unstructured":"Welling, M., Teh, Y.W.: Bayesian learning via stochastic gradient Langevin dynamics. In: International Conference on Machine Learning, pp. 681\u2013688 (2011)"},{"key":"442_CR68","unstructured":"Woodford, O.: Notes on contrastive divergence. Tech., Rep., Department of Engineering Science, University of Oxford (2006)"},{"key":"442_CR69","unstructured":"Xiao, Z., Kreis, K., Kautz, J., Vahdat, A.: Vaebm: A symbiosis between variational autoencoders and energy-based models. In: International Conference on Learning Representations (2021)"},{"key":"442_CR70","unstructured":"Xie, J., Lu, Y., Zhu, S.C., Wu, Y.: A theory of generative ConvNet. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning, Volume\u00a048 of Proceedings of Machine Learning Research, New York, NY, USA, pp. 2635\u20132644. PMLR (2016)"},{"key":"442_CR71","unstructured":"Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: a survey. arXiv preprint arXiv:2110.11334 (2021)"},{"key":"442_CR72","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"issue":"3","key":"442_CR73","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TPAMI.2004.1262324","volume":"26","author":"Y Zheng","year":"2004","unstructured":"Zheng, Y., Li, H., Doermann, D.: Machine printed text and handwriting identification in noisy document images. IEEE Trans. Pattern Anal. Mach. Intell. 26(3), 337\u2013353 (2004). https:\/\/doi.org\/10.1109\/TPAMI.2004.1262324","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-023-00442-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-023-00442-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-023-00442-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T09:08:22Z","timestamp":1692263302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-023-00442-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,22]]},"references-count":73,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["442"],"URL":"https:\/\/doi.org\/10.1007\/s10032-023-00442-x","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,22]]},"assertion":[{"value":"14 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}