Edge detection with multilayer feed forward neural network by using back propagation learning

• Autorzy: Pahsa A.
• Języki publikacji: EN

Abstrakty

EN

In this study, availability of a multilayer feed forward neural network structure by using back propagation learning algorithm in edge detection problem is studied . Based on the edge detection problem, two types of feed forward neural network tree structures are designed. First structure is used with a 9 input for 3x3 mask and the other structure is used with 4 input for 2x2 mask. 6 black and white images are used as input to the feed forward neural network structure. 3 of the 6 images contained simple shape patterns and the rest of the 3 contained complex context. A back propagation learning technique is used in multilayer feed forward neural network that uses gradient algorithm for error minimization in hidden layers. Generated output edge profile images of the given inputs to the multilayer feed forward neural network structure are compared against the conventional edge detection techniques of Canny and Sobel mask operators.

Słowa kluczowe

EN

edge detection; neural network; Canny mask; backpropagation learning

PL

sieć neuronowa

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2008
• Tom: Vol. 13, no 1-2
• Strony: 21--34
• Opis fizyczny: Bibliogr. 12 poz., fot., rys.

Twórcy

autor

Pahsa A.

• Ankara University, Electronics Engineering Department, 06500, Besevler Ankara,

Bibliografia

• [1] C. Gonzales,E. Woods, Digital Image Processing, Second Edition, Prentice Hall publications, 2002.
• [2] A. Tinku, A. K. Ray, Image Processing-Principles and Application, Wiley&Sons Interscience Inc. Publication, pp. 131-143, 2005.
• [3] J. Canny, A Computational Approach To Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, pp. 679-714, 1986.
• [4] B. Fisher, S. Perkins, A. Walker, E. Wolfart, Sobel Edge Detector, Hypermedia Image Processing Reference, Department of Artificial Intelligence, University of Edinburgh, 1994. http://www.cee.hw.ac.uk/hipr/html/sobel.html
• [5] 5. S. Haykin, Neural Networks: A Comprehensive Foundation, Second Edition, Prentice Hall Publications, 1998.
• [6] O. R. Duda, P. E. Hart, G. D. Stork, Pattern Classification, Wiley & Sons Intercience Inc., Second Edition, pp. 282-350.
• [7] S. Mallat, S. Zhong, Characterization of Signals from Multi-Scale Edges, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-14, No 7, pp. 710-732, July 1992.
• [8] A. Talukder, D. Casasent, Multiscale Gabor Wavelet Fusion For Edge Detection in Microscopy Images, Proceedings of SPIE 3391, 336, 1998.
• [9] M. H.-Y. Liao, M.-T. Ko, J.-W. Hsieh, C. F. Kuo, A New Wavelet Based Edge Detector Via Constrained Optimization, Image and Vision Computing, vol. 15, No 7, pp. 511-527, July 1997.
• [10] T. Lindeberg, Edge detection and ridge detection with automatic scale selection, International Journal of Computer Vision, 30, 2, pp. 117-154, 1998.
• [11] H. M. G. Velasco, G. J. C. Orellana, M. Macias, L. J. F. Alligue, A. M. I. Sotoca, Neural Networks based Edges Selector for Boundary Extraction Problems, Image and Vision Computing, vol. 22, Issue 13, pp. 1129-1135, November 2004.
• [12] H. S. Wong, T. Caelli, L. Guan, A Model Based Neural Network for Edge Characterization, Pattern Recognition, vol. 33, Issue 3, pp 427-444, March 2000.