Abstract
Nowadays, Deep Learning is one of the most popular techniques which is used in several fields like handwriting text recognition. This paper presents our propose for a handwritten digit sequences recognition system. Our system, based in two stage model, is composed by Convolutional Neural Networks and Recurrent Neural Networks. Moreover, it is trained using on-demand scheme to recognize numbers from digits of the MNIST dataset. We will see that, with these training samples is not necessary segment or normalize the input images. Average recognition results were on 88,6% of accuracy in numbers of variable-length, between 1 and 10 digits. This accuracy is independent on the number length. Moreover, in most of the wrongly predicted numbers there was only one digit error.
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
Arica, N., Yarman-Vural, F.T.: An overview of character recognition focused on off-line handwriting. Syst. Man Cybern. 31(2), 216–233 (2001)
Bluche, T., Ney, H., Kermorvant, C.: Feature extraction with convolutional neural networks for handwritten word recognition. In: 12th International Conference on Document Analysis and Recognition, pp. 285–289 (2013)
Bluche, T., Ney, H., Kermorvant, C.: A comparison of sequence-trained deep neural networks and recurrent neural networks optical modeling for handwriting recognition. In: Besacier, L., Dediu, A.-H., Martín-Vide, C. (eds.) SLSP 2014. LNCS, vol. 8791, pp. 199–210. Springer, Cham (2014). doi:10.1007/978-3-319-11397-5_15
Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. Adv. Neural Inf. Process. Syst. 20, 161–168 (2008)
Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. Conf. Comput. Vis. Pattern Recognit. 2012, 3642–3649 (2012)
Deng, L.: The MNIST database of handwritten digit images for machine learning research. In: IEEE Signal Processing Magazine, pp. 141–142 (2012)
Graves, A., Eck, D., Beringer, N., Schmidhuber, J.: Isolated digit recognition with LSTM recurrent networks. In: First International Workshop on Biologically Inspired Approaches to Advance Information Technology (2003)
Graves, A., Fernandez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequece data with recurrent neural networks. In: International Conference on Machine Learning, pp. 369–376 (2006)
Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. Adv. Neural Inf. Process. Syst. 21, 545–552 (2009)
Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for improved unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855–868 (2014)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Koerich, A.L., Sabourin, R., Suen, C.Y.: Large vocavulary off-line handwriting recognition: a survey. Pattern Anal. Appl. 6(2), 97–121 (2003)
Krizhesvky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: 26th Advances in Neural Information Processing Systems (NIPS), pp. 1097–1105 (2012)
LeCun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist (1998)
Lu, Y., Sridhar, M.: Character segmentation in handwritten words-an overview. Pattern Recognit. 29(1), 77–96 (1995)
Matan, O., Burges, C.J.C., LeCun, Y., Denker, J.S.: Multi-digit recognition using a space displacement neural network. Neural Inf. Process. Syst. 4, 488–495 (1992)
Patel, M., Thakkar, S.P.: Handwritten character recognition in english: a survey. Int. J. Adv. Res. Comput. Commun. Eng. 4(2), 345–350 (2015)
Plamondon, R., Srihari, S.N.: On-line and off-line handwriting recognition: a comprehensive survey. Pattern Anal. Mach. Intel. IEEE Trans. 22(1), 63–84 (2000)
Seiler, R., Schenkel, M., Eggimann, F.: Off-line cursive handwriting recognition compared with on-line recognition. In: Proceedings of the International Conference on Pattern Recognition IV-7472, pp. 505–509 (1996)
Srivastava, N., Hinton, G., Krizhesvsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Symonian, K., Zisserman, A.: Very deep convolutional networks for large scale image recognition. In: 3rd International Conference on Learning Representation, pp. 1–14 (2015)
Vinayakumar, R., Paul, V.: A survey on recognition and analysis of handwrittten document. Int. J. Comput. Sci. Eng. Technol. 6, 19–23 (2016)
Vinciarelli, A.: A survey on off-line cursive script recognition. Pattern Recognit. 35(7), 1433–1446 (2002)
Acknowledgements
This work was funded by the Spanish Ministry of Economy and Competitiveness under grant number TIN2014-57458-R.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ruiz, V., Gonzalez de Lena, M.T., Sueiras, J., Sanchez, A., Velez, J.F. (2017). A Deep Learning Approach to Handwritten Number Recognition. In: Ferrández Vicente, J., Álvarez-Sánchez, J., de la Paz López, F., Toledo Moreo, J., Adeli, H. (eds) Biomedical Applications Based on Natural and Artificial Computing. IWINAC 2017. Lecture Notes in Computer Science(), vol 10338. Springer, Cham. https://doi.org/10.1007/978-3-319-59773-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-59773-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59772-0
Online ISBN: 978-3-319-59773-7
eBook Packages: Computer ScienceComputer Science (R0)