Abstract
With the increasing popularity of smartphones and services, symbol recognition becomes a challenging task in terms of computational capacity. To our best knowledge, existing methods have focused on effective and fast neural networks architectures, including the ones which deal with the graph symbol representation. In this paper, we propose to optimize the neural networks input rather than the architecture. We compare the performance of several existing graph architectures in terms of accuracy, learning and training time using the advanced skeleton symbol representation. It comprises the inner symbol structure and strokes width patterns. We show the usefulness of this representation demonstrating significant reduction of training time without noticeable accuracy degradation. This makes our approach the worthy replacement of conventional graph representations in symbol recognition tasks.
A. Grigorev, A. Lukoyanov, N. Korobov and P. Kutsevol—Authors contributed equally and listed in alphabetical order.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Palvanov, A., Im Cho, Y.: Comparisons of deep learning algorithms for MNIST in real-time environment. Int. J. Fuzzy Logic Intell. Syst. 18(2), 126–134 (2018)
Zou, X., Duan, S., Wang, L., Zhang, J.: Fast convergent capsule network with applications in MNIST. In: Huang, T., Lv, J., Sun, C., Tuzikov, A.V. (eds.) ISNN 2018. LNCS, vol. 10878, pp. 3–10. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-92537-0_1
Bai, X., Latecki, L.J., Liu, W.-Y.: Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 449–462 (2007)
Fey, M., et al.: SplineCNN: fast geometric deep learning with continuous B-spline kernels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 869–877 (2018)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. Handb. Brain Theory Neural Netw. 3361(10), 255–258 (1995)
Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional neural network committees for handwritten character classification. In: 2011 International Conference on Document Analysis and Recognition, pp. 1135–1139. IEEE (2011)
Mestetskiy, L., Semenov, A.: Binary image skeleton-continuous approach. VISAPP 1, 251–258 (2008)
Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNS. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5115–5124 (2017)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1263–1272 (2017)
Riba, P., Fischer, A., Lladós, J., Fornés, A.: Learning graph distances with message passing neural networks. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2239–2244. IEEE (2018)
Fey, M., Lenssen, J.E.: Fast Graph Representation Learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Yu, P.S.: A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596 (2019)
Shen, W., Zhao, K., Jiang, Y., Wang, Y., Bai, X., Yuille, A.: DeepSkeleton: learning multi-task scale-associated deep side outputs for object skeleton extraction in natural images. IEEE Trans. Image Process. 26(11), 5298–5311 (2017)
Pratikakis, I., Zagoris, K., Barlas, G., Gatos, B.: ICFHR2016 handwritten document image binarization contest (H-DIBCO 2016). In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 619–623. IEEE (2016)
Vinyals, O., Bengio, S., Kudlur, M.: Order matters: sequence to sequence for sets. arXiv preprint arXiv:1511.06391 (2015)
Morris, C., et al.: Weisfeiler and leman go neural: higher-order graph neural networks. AAAI (2019)
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
Grigorev, A., Lukoyanov, A., Korobov, N., Kutsevol, P., Zharikov, I. (2019). Input Simplifying as an Approach for Improving Neural Network Efficiency. In: van der Aalst, W., et al. Analysis of Images, Social Networks and Texts. AIST 2019. Lecture Notes in Computer Science(), vol 11832. Springer, Cham. https://doi.org/10.1007/978-3-030-37334-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-37334-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37333-7
Online ISBN: 978-3-030-37334-4
eBook Packages: Computer ScienceComputer Science (R0)