Comparison of LeNet-5, AlexNet and GoogLeNet models in handwriting recognition

Bartosz Michalski


Department of Computer Science, Lublin University of Technology (Poland)

Małgorzata Plechawska-Wójcik

m.plechawska@pollub.pl
Department of Computer Science, Lublin University of Technology (Poland)

Abstract

The aim of the study was to compare the accuracy of handwriting recognition and the time needed to classify data from the test sets. The Lenet-5, AlexNet and GoogLeNet architectures were used for the research. They are all models of convolutional neural networks. The research was carried out with the use of image databases, handwritten digits MNIST and handwritten letters EMNIST. After the tests, it was found that the GoogLeNet model showed the highest accuracy, and the LeNet-5 the lowest. However, the LeNet-5 model needed the least time to complete the task, and GoogLeNet the most. On the basis of the obtained results, it was found that increasing the complexity of the model positively influences the accuracy of object classification, but significantly increases the demand for computer re-sources.


Keywords:

convolutional neural networks; handwriting classification

D. O. Hebb, The organisation of behaviour: a neuropsychological theory. New York: Science Editions (1949).
  Google Scholar

F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65(6) (1958) 386.
DOI: https://doi.org/10.1037/h0042519   Google Scholar

Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard., W. Hubbard, L. D. Jackel, Backpropagation applied to handwritten zip code recognition. Neural computation 1(4) (1989) 541-551.
DOI: https://doi.org/10.1162/neco.1989.1.4.541   Google Scholar

O. Russakovsky, J. Deng, H. Su, et al. ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis 115 (2015) 211–252. https://doi.org/10.1007/s11263-015-0816-y
DOI: https://doi.org/10.1007/s11263-015-0816-y   Google Scholar

Ü. Budak, A. Şengür, U. Halici, Deep convolutional neural networks for airport detection in remote sensing images. 26th Signal Processing and Communications Applications Conference (SIU) (2018) 1-4, doi: 10.1109/SIU.2018.8404195.
DOI: https://doi.org/10.1109/SIU.2018.8404195   Google Scholar

M. J. Aitkenhead, A. J. S. McDonald. A neural network face recognition system. Engineering Applications of Artificial Intelligence 16(3) (2003) 167-176.
DOI: https://doi.org/10.1016/S0952-1976(03)00042-3   Google Scholar

D. S. Maitra, U. Bhattacharya, S. K. Parui, CNN based common approach to handwritten character recognition of multiple scripts. 13th International Conference on Document Analysis and Recognition (ICDAR) (2015) 1021-1025, doi: 10.1109/ICDAR.2015.7333916.
DOI: https://doi.org/10.1109/ICDAR.2015.7333916   Google Scholar

K. Nygren, Stock prediction–a neural network approach. Royal Instiute of Technology (2004) 1-34.
  Google Scholar

S. S. Baboo, I. K. Shereef, An efficient weather forecasting system using artificial neural network. International journal of environmental science and development 1(4) (2010) 321.
DOI: https://doi.org/10.7763/IJESD.2010.V1.63   Google Scholar

J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (2009) 248–255.
DOI: https://doi.org/10.1109/CVPR.2009.5206848   Google Scholar

Y. LeCun, C. Cortes, The MNIST database of handwritten digits (2005).
  Google Scholar

G. Cohen, S. Afshar, J. Tapson, A. van Schaik, EMNIST: an extension of MNIST to handwritten letters (2017) arXiv:1702.05373.
DOI: https://doi.org/10.1109/IJCNN.2017.7966217   Google Scholar

Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, Gradient-based learning applied to document recognition in Proceedings of the IEEE 86(11) (1998) 2278-2324, doi: 10.1109/5.726791.
DOI: https://doi.org/10.1109/5.726791   Google Scholar

A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks. In F. Pereira, C. Burges, L. Bottou, K. Weinberger, eds., Advances in Neural Information Processing Systems 25. Curran Associates (2012) 1097–1105. arXiv:1803.01164
  Google Scholar

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going Deeper with Convolutions (2014) arXiv:1409.4842.
DOI: https://doi.org/10.1109/CVPR.2015.7298594   Google Scholar

K. O'Shea, R. Nash, An introduction to convolutional neural networks (2015) arXiv preprint arXiv:1511.08458.
  Google Scholar

Grother, P. J, NIST special database 19. Handprinted forms and characters database, National Institute of Standards and Technology (1995).
  Google Scholar

W. S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5(4) (1943) 115-133.
DOI: https://doi.org/10.1007/BF02478259   Google Scholar

E. Lukasik, M. Charytanowicz, M. Milosz, M. Tokovarov, M. Kaczorowska, D. Czerwinski, T. Zientarski, Recognition of handwritten Latin characters with diacritics using CNN. Bulletin of the Polish Academy of Sciences. Technical Sciences 69(1) (2021).
  Google Scholar

Download


Published
2022-06-30

Cited by

Michalski, B., & Plechawska-Wójcik, M. (2022). Comparison of LeNet-5, AlexNet and GoogLeNet models in handwriting recognition. Journal of Computer Sciences Institute, 23, 145–151. https://doi.org/10.35784/jcsi.2919

Authors

Bartosz Michalski 

Department of Computer Science, Lublin University of Technology Poland

Authors

Małgorzata Plechawska-Wójcik 
m.plechawska@pollub.pl
Department of Computer Science, Lublin University of Technology Poland

Statistics

Abstract views: 393
PDF downloads: 243