Convolutional neural model in a TASK of classification images of the isolated digits
Abstract
The analysis of convolutional neural model is done. The software is developed, allowing to train and test convolutional neural networks of base architecture LeNet-5. Efficiency of technique multi training and distortions of training images is shown. The qualifier of images of the isolated figures is constructed. The estimation of stability of its characteristics on examples of known hand-written and font databases is done.
References
1. Головко В.А. Нейронные сети: обучение, организация и применение. М., 2001.
2. Simard P.Y., Steinkraus D., Platt J. // Int. Conf. on Document Analysis and Recognition. 2003. P. 958-963.
3. Hubel D.H., Wiesel T.N. // Journal of Physiology London., 1962. Vol. 15. P 106-154.
4. Fukushima K., Miyake S. // Pattern Recognition. 1982. Vol. 15. P. 455-469.
5. LeCun Y., Kavukvuoglu K., Farabet C. // Proc. Int. Symposium on Circuits and Systems. 2010. P 253-256.
6. LeCun Y., Bottou L., Bengio Y., et. al. // Proceedings of the IEEE. 1998. P. 2278-2324.
7. LeCun Y., Bottou L., Or G.B., et. al. // Springer Lecture Notes in Computer Sciences. 1998. № 1524. P. 5-50.
8. LeCun Y. The MNIST database of handwritten digits // http://yann.lecun.com/exdb/mnist.
9. Grother P.J. Nist special database 19 - handprinted forms and characters database // National Institute of Standards and Thechnology (NIST), Tech. Rep. 1995.
10. Осовский С. Нейронные сети для обработки информации. М., 2002.
11. Optdigits database // http://archive.ics.uci.edu/ml/machine-learning-databases/optdigits.
Review
For citations:
Kuzmitsky N.N. Convolutional neural model in a TASK of classification images of the isolated digits. Doklady BGUIR. 2012;(7):65-71. (In Russ.)
Views: 470
Email this article 