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.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. Phillips, P.J., Grother, P., Ross, J., Blackburn, D., Tabassi, E., Bone, M.: Face Recognition Vendor Test 2002: Evaluation Report. (March 2003).
2. Kotzer, T., Rosen, J., Shamir, J.: Phase extraction pattern recognition. Appl. Opt. 31, 1126–1137 (1992).
3. H.H. Szu, 'Review of Wavelet Transforms for Pattern Recognition, ', Wavelet Applications III, Proceedings of SPIE, vol. 2762, 1996, p.2–22.
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).
5. Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York (1981).