Erkan BEŞDOK, Mehmet ERLER, Şeref SAĞIROĞLU

Yapay sinir ağları ile görüntü kodlama

Bu çalışmada, yapay sinir ağlarına (YSA) dayalı resim kodlama tekniği sunulmuştur. YSA ile resim kodlama DC bileşenler kullanılarak gerçekleştirilmiştir. YSA eğitiminde geliştirilmiş delta-bar-delta algoritması kullanılmıştır. Ayrık kosinüs transformuyla elde edilen resim kodlamaya göre YSA ile yapılan kodlamada daha iyi sonuç elde edilmiştir.

Image coding with the use of artificial neural networks

This study presents a new approach based on artificial neural networks (ANNs) to code the images in an efficient manner. ANNs achived the image coding with the use of DC elements. The extended delta-bar-delta algorithm is used to train the neural network. The results show that image coding" using ANNs is achieved with high accuracy in comparision with the classical discrete cosine transformation.

___

1.Rosenfeld, A. and A.C. Kak (1982), Digital Picture Processing, Second Edition. Academic Press, New York.
2.Pratt, W.K. (1991), Digital Image Processing, Second Edition Wiley, New York.
3.Sid-Ahmed, M. A. (1995), Image Processing, McGraw-Hill, New York.
4.Sonka, M., Hlavac, V. and Boyle, R. (1999), Image processing, analysis, and machine vision, Second Edition, BROOK/COLE Publishing Company, Pasific Grove, USA.
5.Castleman, K.R. (1996), Digital Image Processing, Prentice-Hall, Englewood Cliffs. New Jersey.
6.Rao, K.R. and Yip, P. (1990), Discrete Cosine Transform, Algorithms, Advantages. Applications, Academic Press,Boston.
7.Simpson, P. K. (1990), Artificial Neural Systems Foundation, Paradigms, Application and Implementation, Permagnon Press, ISBN 0-08-037895-1.
8.Haykin, S. (1994), Neural Networks: A Comprehensive Foundation. ISBN 0-02-352761-7, Macmillan College Publishing Company, New York, USA.
9.Pham, D. T. and Sagiroglu, S. (1996), Three methods of training multi-layer perceptrons to model a robot sensor. Robolica, vol. 13, pp. 531-538.
10.Minai, A. A. and Williams, R. D. (1990), Acceleration of Backpropagation Through Learning Rate and Momentum Adaptation, Int. Joint Conf. on Neural Networks. Washington. DC. vol. 1, pp. 676-679.
11.Jacobs, R. A. (1988), Increased Rate of Convergence Through Learning Rate Adaptation, Neural Networks, V.I, pp.295-307.
12.Neural Computing (1996), A Technology Handbook for Professional II/PLUS and Neural Works Explorer", Pittsburgh: NeuralWare, Inc., Technical Publications Group.
13.Browne, A. (1997), Neural Network Analysis, Architectures and Applications ISBN: 0750304995, lop Pub., New York.
14.Warwick, K., Taylor, J. G. and Kurkova, V. (1997), Dealing with Complexity^ Neural Network Approach. ISBN:3540761608 Publisher:Springer-Verlag New York.
15.Masters, T. (1996), Practical Neural Network Recipes in C++, ISBN: 0124790402 Publisher: Harcourt Brace & Company, New York.
16.Beşdok, E., Raster Veritabanlarının Yapay Sinir Ağları ile Yorumlanması, Doktora Tezi, İTÜ Fen Bilimleri Ensititüsü, Ekim 2000, İstanbul.