nach oben

Erschienen in:

2022 | OriginalPaper | Buchkapitel

A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian

verfasst von : Martin Maarand, Yngvil Beyer, Andre Kåsen, Knut T. Fosseide, Christopher Kermorvant

Erschienen in: Document Analysis Systems

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

In this paper, we introduce an open database of historical handwritten documents fully annotated in Norwegian, the first of its kind, allowing the development of handwritten text recognition models (HTR) in Norwegian. In order to evaluate the performance of state-of-the-art HTR models on this new base, we conducted a systematic survey of open-source HTR libraries published between 2019 and 2021, identified ten libraries and selected four of them to train HTR models. We trained twelve models in different configurations and compared their performance on both random and scripter-based data splitting. The best recognition results were obtained by the PyLaia and Kaldi libraries which have different and complementary characteristics, suggesting that they should be combined to further improve the results.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Keyword Spotting with Quaternionic ResNet: Application to Spotting in Greek Manuscripts

Nächstes Kapitel Open Source Handwritten Text Recognition on Medieval Manuscripts Using Mixed Models and Document-Specific Finetuning

https://www.nb.no/forskning/nb-kilder/.

https://www.ibsen.uio.no/.

https://emunch.no/english.xhtml.

An example of this is Anker & Schjønsby’s Lyset i flatene: i arkivet etter Harriet Backer (2021).

The model architectures can be seen here: https://github.com/arthurflor23/handwritten-text-recognition/tree/master/doc/arch.

Arora, A., et al.: Using ASR methods for OCR. In: International Conference on Document Analysis and Recognition (2019)

Augustin, E., Brodin, J.M., Carré, M., Geoffrois, E., Grosicki, E., Prêteux, F.: RIMES evaluation campaign for handwritten mail processing. In: International Conference on Document Analysis and Recognition, p. 5 (2006)

Chammas, E., Mokbel, C., Likforman-Sulem, L.: Handwriting recognition of historical documents with few labeled data. In: International Workshop on Document Analysis Systems, pp. 43–48. IEEE (2018)

Coquenet, D., Chatelain, C., Paquet, T.: Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network. In: International Conference on Frontiers in Handwriting Recognition, pp. 19–24 (2020)

Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. (2022)

Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: International Conference on Machine Learning, pp. 369–376 (2006)

Hegghammer, T.: OCR with tesseract, Amazon textract, and Google document AI: a benchmarking experiment. J. Comput. Soc. Sci. (2021)

Hodel, T., Schoch, D., Schneider, C., Purcell, J.: General models for handwritten text recognition: feasibility and state-of-the art. German kurrent as an example. J. Open Humanit. Data 7(13), 1–10 (2021)

Hussain, R., Raza, A., Siddiqi, I., et al.: A comprehensive survey of handwritten document benchmarks: structure, usage and evaluation. J. Image Video Proc. 2015, 46 (2015). https://doi.org/10.1186/s13640-015-0102-5CrossRef

10.

Jørgensen, F., Aasmoe, T., Ruud Husevåg, A.S., Øvrelid, L., Velldal, E.: NorNE: annotating named entities for Norwegian. In: Language Resources and Evaluation Conference (2020)

11.

Kang, L., Riba, P., Rusiñol, M., Fornés, A., Villegas, M.: Distilling content from style for handwritten word recognition. In: International Conference on Frontiers in Handwriting Recognition (2020)

12.

Kang, L., Toledo, J.I., Riba, P., Villegas, M., Fornés, A., Rusiñol, M.: Convolve, attend and spell: an attention-based sequence-to-sequence model for handwritten word recognition. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 459–472. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_32CrossRef

13.

Kiessling, B., Tissot, R., Stokes, P., Stökl Ben Ezra, D.: eScriptorium: an open source platform for historical document analysis. In: International Conference on Document Analysis and Recognition Workshops, vol. 2, p. 19 (2019)

14.

Kummervold, P.E., de la Rosa, J., Wetjen, F., Brygfjeld, S.A.: Operationalizing a national digital library: the case for a norwegian transformer model. In: Nordic Conference on Computational Linguistics (2021)

15.

Li, M., et al.: Trocr: transformer-based optical character recognition with pre-trained models (2021). https://arxiv.org/abs/2109.10282

16.

Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. IJDAR 5, 39–46 (2002). https://doi.org/10.1007/s100320200071CrossRefMATH

17.

Michael, J., Weidemann, M., Labahn, R.: Htr engine based on nns p 3 optimizing speed and performance-htr +. Technical report, READ-H2020 Project 674943 (2018)

18.

Muehlberger, G., et al.: Transforming scholarship in the archives through handwritten text recognition: transkribus as a case study. J. Doc. (2019)

19.

Nesse, A., Sandøy, H.: Norsk Språkhistorie IV: Tidslinjer. Novus, Oslo (2018)

20.

Neto, A.F.S., Bezerra, B.L.D., Toselli, A.H., Lima, E.B.: HTR-flor++: a handwritten text recognition system based on a pipeline of optical and language models. In: ACM Symposium on Document Engineering (2020)

21.

Nguyen, T.T.H., Jatowt, A., Coustaty, M., Nguyen, N.V., Doucet, A.: Deep statistical analysis of OCR rrrors for effective post-OCR processing. In: Joint Conference on Digital Libraries (2019)

22.

Ortiz, P., Burud, S.: Bert attends the conversation: improving low-resource conversational asr (2021). https://arxiv.org/abs/2110.02267

23.

Povey, D., et al.: Purely sequence-trained neural networks for asr based on lattice-free mmi. In: Interspeech, pp. 2751–2755 (2016)

24.

Puigcerver, J., Mocholí, C.: PyLaia (2018). https://github.com/jpuigcerver/PyLaia

25.

Strauß, T., Leifert, G., Labahn, R., Mühlberger, G.: Competition on automated text recognition on a read dataset. In: International Conference on Frontiers in Handwriting Recognition (2018)

26.

Sánchez, J.A., Romero, V., Toselli, A., Villegas, M., Vidal, E.: A set of benchmarks for handwritten text recognition on historical documents. Pattern Recogn. 94, 122–134 (2019)CrossRef

27.

Toiganbayeva, N., et al.: KOHTD: kazakh offline handwritten text dataset (2021). https://arxiv.org/abs/2110.04075

28.

Yousef, M., Bishop, T.E.: Origaminet: weakly-supervised, segmentation-free, one-step, full page textrecognition by learning to unfold. In: Conference on Computer Vision and Pattern Recognition (2020)

Titel: A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian
verfasst von: Martin Maarand
Yngvil Beyer
Andre Kåsen
Knut T. Fosseide
Christopher Kermorvant
Verlag: Springer International Publishing
Buch: Document Analysis Systems
Print ISBN: 978-3-031-06554-5

Electronic ISBN: 978-3-031-06555-2

Copyright-Jahr: 2022
DOI: https://doi.org/10.1007/978-3-031-06555-2_27

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner