Improved method of handwritten digit recognition tested on MNIST database

Image and Vision Computing

Volumn 22, Issue 12 SPEC. ISS., 2004, Pages 971-981

  Kussul, Ernst ^a   Baidyk, Tatiana ^a  

^a UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO   (Mexico)

Author keywords

Handwritten digit recognition; LImited Receptive Area neural classifier; Microdevice assembly; MNIST database

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL METHODS; DATABASE SYSTEMS; IMAGING TECHNIQUES; MATHEMATICAL OPERATORS; PATTERN RECOGNITION; PROBLEM SOLVING; SENSORS;

HANDWRITTEN DIGIT RECOGNITION; LIMITED RECEPTIVE AREA NEURAL CLASSIFIER; MICRODEVICE ASSEMBLY; MNIST DATABASE;

COMPUTER VISION;

EID: 4344611721     PISSN: 02628856     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.imavis.2004.03.008     Document Type: Conference Paper

References (15)

1. Baidyk T., Kussul E. Application of neural classifier for flat image recognition in the process of microdevice assembly. Proceedings of the International Joint Conference on Neural Networks, Hawaii, USA. 1:2002;160-164.
2. Belongie S., Malik J., Puzicha J. Matching shapes. Proceedings of Eighth IEEE International Conference on Computer Vision ICCV. 1:2001;454-461.
3. Belongie S., Malik J., Puzicha J. Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence. 24:(4):2002;509-522.
4. Kiu C.-K., Nakashima K., Saco H., Fujisawa H. Handwritten digit recognition using state-of-the-art techniques. Proceedings of the IEEE Eighth International Workshop on Frontiers in Handwritten Recognition, Ontario, Canada. 2002;320-325.
5. Clarke T.J.W., Prager R.W., Fallside F. The modified Kanerva model: theory and results for real-time word recognition. IEE Proceedings-F. 138:(1):1991;25-31.
6. Hoque M.S., Fairhurst M.C. A moving window classifier for off-line character recognition. Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition. 2000;595-600.
7. Kussul E.M., Baidyk T.N. Neural random threshold classifier in OCR application. Proceedings of the Second All-Ukrainian International Conference UkrOBRAZ'94, Ukraine. 1994;154-157.
8. Kussul E.M., Baidyk T.N. Improved method of handwritten digit recognition. Proceedings of the 15th International Conference on Vision Interface, Canada. 2002;192-197.
9. Kussul E.M., Baidyk T.N., , et al. Rosenblatt perceptrons for handwritten digit recognition. Proceedings of International Joint Conference on Neural Networks IJCNN. 2:2001;1516-1520.
10. Kussul E.M., Baidyk T.N., Lukovitch V.V., Rachkovskij D.A. Adaptive high performance classifier based on random threshold neurons. in: Cybernetics and Systems'94. 1994;World Scientific, Singapore. pp. 1687-1695.
11. Kussul E.M., Rachkovskij D., Wunsch D. The random subspace coarse coding scheme for real-valued vectors. Proceedings of IEEE International Joint Conference on Neural Networks, Washington. 1999;450-455.
12. LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 86:(11):1998;2278- 2344.
13. Ososkov G. Effective neural network approach to image recognition and control. Proceedings of International Conference on Physics and Control. 1:2003;242-246.
14. Rosenblatt F. Principles of Neurodynamics. 1962;Spartan Books, New York.
15. Vitabile S., Gentile A., Sorbello F. A neural network based automatic road signs recognizer. Proceedings of the 2002 International Joint Conference on Neural Networks. 3:2002;2315-2320.