Abstract
In this paper, an approach to text/non-text stroke classification for on-line handwriting recognition is proposed. This approach allows to improve classification accuracy when the stroke’s context is absent. Having a label for the input stroke, we set this label for a feature vector which corresponds to each timestamp of the given input stroke. A trained neural network classifies each timestamp for the given input sequence. Finally, a decoder assigns a class label to the whole stroke. This approach was tested on the online handwritten dataset IAMonDO in on-line mode and has shown 98.5% accuracy. This approach could be used for other time-series classification tasks when the context information is not available.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Graves, A., Liwicki, M., Bunke, H., Schimdhuber, J., Fernández, S., Bertolami, R.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855–868 (2009)
Khomenko, V., Degtyarenko, I., Radyvonenko, O., Bokhan, K.: Text/shape classifier for mobile applications with handwriting input. Int. J. Doc. Anal. Recognit. 19(4), 369–379 (2016)
Van Phan, T., Nagakawa, M.: Text/non-text classification in online handwritten documents with recurrent neural networks. In: Proceedings of the ICFHR, pp. 23–28 (2014)
Van Phan, T., Nagakawa, M.: Combination of global and local contexts for text/non-text classification in heterogeneous online handwritten documents. Pattern Recognit. 51, 112–124 (2016)
Khomenko, V., Degtyarenko, I., Radyvonenko, O., Bokhan, K., Volkoviy, A.: Document structure analysis for online handwriting recognition in mobile applications. In: Proceedings of ICAPR 2017. https://www.isical.ac.in/icapr17/apl.php. (in publish)
Bresler, M., Průša, D., Hlaváč, V.: Online recognition of sketched arrow-connected diagrams. Int. J. Doc. Anal. Recognit. 19(3), 253–267 (2016)
Ghodrati, A., Blagojevic, R., Guesgen, H., Marsland, S., Plimmer, B.: The role of grouping in sketched diagram recognition. ACM Press (2018). https://doi.org/10.1145/3229147.3229160
Fahmy, A., Abdelhamid, W., Atiya, A.: Interactive sketch recognition framework for geometric shapes. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018, Part V. LNCS, vol. 11305, pp. 323–334. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04221-9_29
Jain, A., Namboodiri, A., Subrahmonia, J.: Structure in online documents. In: Proceedings of the the ICDAR, pp. 844–848 (2001)
Rossignol, S., Willems, D., Neumann, A., Vuurpijl, L.: Mode detection and incremental recognition. In: Proceedings of the ICFHR, pp. 597–602 (2004)
Willems, D., Rossignol, S., Vuurpijl, L.: Features for mode detection in natural online pen input. In: Proceedings of 12th Biennial Conference of the International Graphonomics Society, pp. 113–117 (2005)
Otte, S., Krechel, D., Liwicki, M., Dengel, A.: Local feature based online mode detection with recurrent neural networks. In: Proceedings of the ICFHR, pp. 533–537 (2012)
Weber, M., Liwicki, M., Schelske, Y., Schoelzel, C., Strauß, F., Dengel, A.: A MCS for online mode detection: evaluation on penabled multi-touch interfaces. In: Proceedings of the ICDAR, pp. 957–961 (2011)
Indermühle, E., Bunke, H., Shafait, F., Breuel, T.: Text vs. non-text distinction in online handwritten documents. In: Proceedings of the 25th Annual ACM Symposium on Applied Computing, vol. 1, pp. 3–7 (2010)
Indermühle, E., Liwicki, M., Bunke, H.: IAMonDo database: an online handwritten document database with non-uniform contents. In: Proceedings of 9th International Workshop on Document Analysis Systems, pp. 97–104 (2010)
Indermühle, E., Frinken, V., Bunke, H.: Mode detection in online handwritten documents using BLSTM neural networks. In: Proceedings of the ICFHR, pp. 302–307 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Polotskyi, S., Deriuga, I., Ignatova, T., Melnyk, V., Azarov, H. (2019). Improving Online Handwriting Text/Non-text Classification Accuracy Under Condition of Stroke Context Absence. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science(), vol 11506. Springer, Cham. https://doi.org/10.1007/978-3-030-20521-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-20521-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20520-1
Online ISBN: 978-3-030-20521-8
eBook Packages: Computer ScienceComputer Science (R0)