Abstract
The present work is motivated by the problem of mathematical handwriting recognition where symbols are represented as parametric plane curves in a Legendre-Sobolev basis. An early work showed that approximating the coordinate functions as truncated series in a Legendre-Sobolev basis yields fast and effective recognition rates. Furthermore, this representation allows one to study the geometrical features of handwritten characters as a whole. These geometrical features are equivalent to baselines, bounding boxes, loops, and cusps appearing in handwritten characters. The study of these features becomes a crucial task when dealing with two-dimensional math formulas and the large set of math characters with different variations in style and size.
In an early paper, we proposed methods for computing the derivatives, roots, and gcds of polynomials in Legendre-Sobolev bases to find such features without needing to convert the approximations to the monomial basis. Furthermore, in this paper, we propose a new formulation for the conversion matrix for constructing Legendre-Sobolev representation of the coordinate functions from their moment integrals.
Our findings in employing parametrized Legendre-Sobolev approximations for representing handwritten characters and studying the geometrical features of such representation has led us to develop two Maple packages called LegendreSobolev and HandwritingRecognitionTesting. The methods in these packages rely on Maple’s linear algebra routines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
This package is publicly available at www.maplesoft.com/applications/view.aspx?SID=154553.
- 2.
This package is publicly available at www.maplesoft.com/applications/view.aspx?SID=154553.
References
Althammer, P.: Eine Erweiterung des Orthogonalitätsbegriffes bei Polynomen und deren Anwendung auf die beste approximation. J. Reine Ang. Math. 211, 192–204 (1962)
Alvandi, P., Watt, S.M.: Real-time computation of Legendre-Sobolev approximations. In: SYNASC, pp. 67–74 (2018)
Alvandi, P., Watt, S.M.: Handwriting feature extraction via Legendre-Sobolev matrix representation (2019, preprint)
Barnett, S.: A companion matrix analogue for orthogonal polynomials. Linear Algebr. Appl. 12(3), 197–202 (1975)
Carballo, G., Álvarez Nodarse, R., Dehesa, J.S.: Chebychev polynomials in a speech recognition model. Appl. Math. Lett. 14(5), 581–585 (2001)
Char, B.W., Watt, S.M.: Representing and characterizing handwritten mathematical symbols through succinct functional approximation. In: ICDAR, vol. 2, pp. 1198–1202 (2007)
Golubitsky, O., Watt, S.M.: Online stroke modeling for handwriting recognition. In: CASCON, pp. 72–80 (2008)
Golubitsky, O., Watt, S.M.: Online computation of similarity between handwritten characters. In: Document Recognition and Retrieval XVI, Part of the IS&T-SPIE Electronic Imaging Symposium, pp. C1–C10 (2009)
Golubitsky, O., Watt, S.M.: Online recognition of multi-stroke symbols with orthogonal series. In: ICDAR, pp. 1265–1269 (2009)
Hausdorff, F.: Summationsmethoden und Momentfolgen. I. Math. Z. 9, 74–109 (1921)
Hausdorff, F.: Summationsmethoden und Momentfolgen. II. Math. Z. 9, 280–299 (1921)
Hu, R., Watt, S.M.: Identifying features via homotopy on handwritten mathematical symbols. In: SYNASC, pp. 61–67 (2013)
Wang, K., An, N., Li, B.N., Zhang, Y., Li, L.: Speech emotion recognition using Fourier parameters. IEEE Trans. Affect. Comput. 6(1), 69–75 (2015)
Zhiqi, Y.: Gesture learning and recognition based on the Chebyshev polynomial neural network. In: 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference, pp. 931–934 (2016)
Zhu, L., Zhu, S.: Face recognition based on orthogonal discriminant locality preserving projections. Neurocomputing 70(7), 1543–1546 (2007). Advances in Computational Intelligence and Learning
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Alvandi, P., Watt, S.M. (2020). The LegendreSobolev Package and Its Applications in Handwriting Recognition. In: Gerhard, J., Kotsireas, I. (eds) Maple in Mathematics Education and Research. MC 2019. Communications in Computer and Information Science, vol 1125. Springer, Cham. https://doi.org/10.1007/978-3-030-41258-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-41258-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41257-9
Online ISBN: 978-3-030-41258-6
eBook Packages: Computer ScienceComputer Science (R0)