anbul 2004 
lages using 
ation feed- 
plying the 
competitive 
| multilayer 
re shown in 
competitive 
competitive 
'd multilayer 
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B7. Istanbul 2004 
  
S. CONCLUSIONS 
The advantages, stable training results and no requirement of a 
priori knowledge provided by the simple competitive learning, and 
optimization for preventing fixation to the local minima provided 
by simulated annealing, are integrated in this modified model. 
Like most. competitive learning models, this modified model can 
be applied in different areas such as computer vision, pattern 
classification, industrial product inspection, etc. In this study, the 
results of the proposed combined technique are compared with the 
results of the backpropagation feed-forward neural networks used 
to classify the same image. The one-hidden layer feed-forward 
network trained with backpropagation algorithm was developed. 
The preliminary results showed that the modified competitive 
learning networks are promising. The time complexity and the 
overall classification accuracy assessment will be performed in 
our experiments. 
REFERENCES 
1. Thomas, I. L., Benning, V. M., and Ching, N. P., 1987. 
Classification of Remotely-Sensed Images, Adam Hilger. 
2. Schowengerdt, R. A., 1983. Techniques for Image 
Processing and Classification in Remote Sensing, 
Academic Press, Inc. 
3. Lillesand, T. M. and Kiefer, R. W., 1987. Remote Sensing 
and Image Interpretation, John Wiley & Sons, Inc. 
4. Bishop C.M. 1995. Neural Networks for Pattern 
Recognition, Oxford. 
5. Hertz, J., Krogh A., and Palmer, R., 1991. Introduction to 
the Theory of Neural Computation, Addison-Wesley. 
6. Lippmann, R. P., 1989. Pattern Recognition Using Neural 
Networks, /EEE Comm. Mag., 27 (11), pp. 47-63. 
7. Ahalt, S. C., Krishnamurphy, A. K. Chen, and Melton, D. 
E., 1990. Competitive Learning Algorithms for Vector 
Quantization, Neural Networks, 3, pp. 277-290. 
8. Hung, C. C,, 1993. Competitive Learning Networks for 
Unsupervised Training, Int. J. Remote Sensing, Vol. 14, 
No. 12, pp. 2411-2415. 
9. Atur, V. Hung, C.C., and Coleman, T.L., 1999. An 
Artificial Neural Network for Classifying and Predicting 
Soil Moisture and Temperature Using  Levenberg- 
Marquardt Algorithm, Proceedings of IEEE Southeastcon 
'99, Lexington, KY, pp. 10-13. 
10. D. L. Civco and Y. Wang, 1994. Classification of 
Multispectral, Multitemporal, Multisource Spatial Data 
Using Artificial Neural Networks, Proceedings of 
ASPRS/ACSM Annual Convention & Exposition, Reno, 
Nevada, pp. 123-133. 
I1. T. A. Warner and M. Shank, 1997. An Evaluation of the 
Potential for Fuzzy Classification of Multispectral Data 
Using Artificial Neural Networks, Photogrammetric 
Engineering & Remote Sensing, Vol. 63, No. 11, pp. 1285- 
1294. 
12. G. M. Foody and M. K. Arora, 1997. An Evaluation of 
Some Factors Affecting the Accuracy of Classification by 
an Artificial Neural Network, Int. J. Remote Sensing, Vol. 
18, No. 4, pp. 799-810. 
13. Alabas, C., Atiparmak, F., and Dengiz, B, 1999. The 
Optimization of Number of Kanbans with Genetic 
Algorithms, Simulated Annealing, and Tabu Search, Gazi 
University, Department of Industrial Engineering. 
14. Battiti, R., and Tecchiolli, G., 1992. Simulated Annealing 
and Tabu Search in the Long Run: A Comparison on QAP 
Tasks, ORSA Journal on Computing, 6 , pp. 126-140. 
107 
ACKNOWLEDGEMENTS 
The authors, Hung and Coleman, wish to acknowledge the 
support of the Center for Hydrology, Soil Climatology, and 
Remote Sensing (HSCaRS) staff. Contribution by the HSCaRS 
Research Center, Department of Plant and Soil Sciences, the 
Agricultural Experiment Station, Alabama A&M University, 
Normal, AL 35762. Journal no. 538. Research supported by 
NAG5-10721 from the National Aeronautics and Space 
Administration (NASA), Washington, DC, USA. Any use of 
trade, product, or firm names is for descriptive purposes only 
and does not imply endorsement by the U.S. Government.