Feature Extraction by Using Non-linear and Unsupervised Neural Networks
Abstract:
Feature extraction is fairly popular in pattern recognition and classification of images. In this paper we propose an unsupervised learning algorithm for neural networks that are used in feature extraction problem. These learning algorithms use genetic algorithm as a searching technique for global minimum of error performance surface and LMS algorithm for final convergence to the global minimum. These learning algorithms used Sammon`s stress as criterion for getting feature with maximum inter pattern distances and minimum intra pattern distances. A common attribute of these learning algorithms is that they are adaptive in nature, which makes them suitable in environments when the distribution of patterns in the feature space changes with respect to time.
How to cite this article
A. Jalil, I.M. Qureshi , A. Naveed and T.a. Cheema , 2003. Feature Extraction by Using Non-linear and Unsupervised Neural Networks. Information Technology Journal, 2: 40-43.
REFERENCES
Abbas, H.M. and M.M. Fahmy, 1992. A neural model for adaptive Karhunen Loeve transformation (KLT). Int. Joint Conf. Neural Networks, 2: 975-980.
Direct Link
Baldi, P. and K. Hornik, 1989. Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks, 2: 53-58.
CrossRef
Jain, B.G., K. Anil and C.D. Richard, 1981. Evaluation of projection algorithms. Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, (TPAMI'81), Michigan State University, East Lansing, MI., pp: 701-708.
Chien, Y., 1978. Interactive Pattern Recognition. Marcel Dekker, New Jersey
Chambers, L., 1995. Practical Handbook of Genetic Algorithm Application. Vol. 1, CRC Press, UK
Davis, L., 1991. Handbook of Genetic Algorithms. 1st Edn., Van Nostrand Reinhold, New York, USA., ISBN-13: 9780442001735, Pages: 385
Huang, W.Y. and R.P. Lippmann, 1987. Comparisons between neural net and conventional classifiers. Proceedings of the IEEE 1st International Conference Neural Networks, June 1987, San Diego, CA., pp: 485-493.
Hornikand, K. and C.M. Kuan, 1992. Convergence analysis of local feature extraction algorithms. Neural Networks, 5: 229-240.
Direct Link
Jain, A.K. and J. Mao, 1992. Artificial neural network for nonlinear projection of multivariatedata. Int. Joint Conf. Neural Networks, 3: 335-340.
CrossRef Direct Link
Freeman, J.A. and M. David, 1999. Skapura. Addison-Wesley, UK
Khotanzad, A. and Y.H. Hong, 1988. Rotation invariant pattern recognition using Zernike moments. Proc. 9th Int. Conf. Pattern Recogn., 1: 326-328.
Direct Link
Kim, H. and K. Nam, 1995. Object recognition of one-DOF tools by a back-propagation neural net. IEEE Trans. Neural Networks, 6: 484-487.
Direct Link
Khotanzad, A. and J.H. Lu, 1990. Classification of invariant image representations using a neural network. IEEE Trans. Acoust. Speech Signal Process., 38: 1028-1038.
Direct Link
Haykin, S., 1998. Neural Networks: A Comprehensive Foundation. 2nd Edn., Prentice Hall, Englewood Cliffs, NJ., USA., ISBN-10: 0132733501, pp: 842
© Science Alert. All Rights Reserved