Adaptive Neural Network for Image Edge Detection

Article Preview

Abstract:

This paper presents a neural network adaptive image edge detection method, and from neural network theory, this paper gives the formula of adaptive neural network algorithm; quantitative given the momentum factor and error, momentum factor and error on the weight vector of norm of the gradient of the quantitative relationship; and gives the algorithm flow diagram. Through experiment we get the conclusion: by using this adaptive neural network for image edge detection is feasible, and it has good generalization ability.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 524-527)

Pages:

3792-3796

Citation:

Online since:

May 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Phillips, P.J., Grother, P., Ross, J., Blackburn, D., Tabassi, E., Bone, M.: Face Recognition Vendor Test 2002: Evaluation Report. (March 2003)

DOI: 10.6028/nist.ir.6965

Google Scholar

[2] Kotzer, T., Rosen, J., Shamir, J.: Phase extraction pattern recognition. Appl. Opt. 31, 1126–1137 (1992)

DOI: 10.1364/ao.31.001126

Google Scholar

[3] H.H. Szu, ''Review of Wavelet Transforms for Pattern Recognition,'' Wavelet Applications III, Proceedings of SPIE, vol. 2762, 1996, p.2–22.

DOI: 10.1117/12.236044

Google Scholar

[4] Yan, P.F.: Some Views on the Research of Multilayer Feed Forward Neural Networks. Act a Automatic a Sonica 23 (1997) 129–135 (in Chinese)

Google Scholar

[5] Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York (1981)

Google Scholar

[6] Yu, J., Yang, M.S.: Optimality Test for Generalized FCM and Its Application to Parameter Selection. IEEE Transactions on Fuzzy Systems 13 (2005) 164–176.

DOI: 10.1109/tfuzz.2004.836065

Google Scholar

[7] Ahmad, Z., Zhang, J.: A Comparison of Different Methods for Combining Multiple Neural Networks Models. Proceedings of International Joint Conference on Neural Networks, Vol. 1 (2002) 828–833.

DOI: 10.1109/ijcnn.2002.1005581

Google Scholar