Recognition of Patterns Without Feature Extraction by GRNN
Automatic pattern recognition is a very important task in many applications such as image segmentation, object detection, etc. This work aims to find a new approach to automatically recognize patterns such as 3D objects and handwritten digits based on a database using General Regression Neural Networks (GRNN). The designed system can be used for both 3D object recognition from 2D poses of the object and handwritten digit recognition applications. The system does not require any preprocessing and feature extraction stage before the recognition. Simulation results show that pattern recognition by GRNN improves the recognition rate considerably in comparison to other neural network structures and has shown better recognition rates and much faster training times than that of Radial Basis Function and Multilayer Perceptron networks for the same applications.
Unable to display preview. Download preview PDF.
- 1.Li, B.-Q., Li, B.: Building pattern classifiers using convolutional neural networks. In: International Joint Conference on Neural Networks, IJCNN’99, 10-16 July 1999, vol. 5, pp. 3081–3085 (1999)Google Scholar
- 3.Specht, D.F.: Enhancements to probabilistic neural network. In: Proc. Int. Joint Conf. Neural Network, vol. 1, pp. 761–768 (1991)Google Scholar
- 4.Zhao, L.-W., Luo, S.-W., Liao, L.-Z.: 3D object recognition and pose estimation using kernel PCA. In: Proceedings of 2004 International Conference on Machine Learning and Cybernetics, 26–29 Aug. 2004, vol. 5, pp. 3258–3262 (2004)Google Scholar
- 5.Okamoto Jr., J., Milanova, M., Bueker, U.: Active perception system for recognition of 3D objects in image sequences. In: International Workshop on Advanced Motion Control - AMC’98, Coimbra, 29 June-1 July 1998, pp. 700–705 (1998)Google Scholar
- 8.Fasel, B.: Head-pose invariant facial expression recognition using convolutional neural networks. In: Fourth IEEE International Conference on Multimodal Interfaces, 14-16 Oct. 2002, pp. 529–534 (2002)Google Scholar
- 9.Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: Seventh International Conference on Document Analysis and Recognition, 3-6 Aug. 2003, pp. 958–963 (2003)Google Scholar
- 10.Heimes, F., van Heuveln, B.: The normalized radial basis function neural network. In: IEEE International Conference on Systems, Man, and Cybernetics, 11-14 Oct. 1998, vol. 2, pp. 1609–1614 (1998)Google Scholar
- 11.Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library (COIL-100). Technical Report No. CUCS-006-96, Department of Computer Science Columbia University New York, N.Y. 10027Google Scholar