Designing pruned neighborhood neural networks for object extraction from noisy background

• Autorzy: Bhattacharyya S. , Dutta P.
• Języki publikacji: EN

Abstrakty

EN

Refinement of neural network architectures by pruning the network interconnections reduces the computational overhead associated with the tasks for which the network is employed. A fuzzy set theoretic approach for designing pruned neighborhood topology-based neural networks for efficient extraction of objects from a noisy background, is presented in this paper. Pruning of the network architecture Is achieved by means of a judicious selection of the participating nodes of the neighborhood topology-based neural network using the fuzzy cardinality measures of the object scene. An application of the proposed methodology for designing a pruned multilayer self organizing neural network for the extraction of binary and gray scale objects from noisy backgrounds with different noise levels is demonstrated. The results obtained are compared with the outputs obtained with the conventional fully connected network architecture of the same network. Comparative results show a significant reduction in the architecture of the network with increasing noise levels for both the binary and gray scale images. Moreover, the qualities of the extracted images obtained using the pruned network architecture are found to be better than those obtained using the conventional fully connected architecture.

Słowa kluczowe

EN

object extraction; neighborhood neural networks; fuzzy cardinality; pruned neural networks

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2006
• Tom: Vol. 31, No. 2
• Strony: 105--134
• Opis fizyczny: Bibliogr. 35 poz.

Twórcy

autor

Bhattacharyya S.

autor

Dutta P.

• Department of Computer Science & Information Technology, University of Technology, The University of Burdwan, Burdwan-713 104, India,

Bibliografia

• [1] A. Ghosh and A. Sen: Soft Computing Approach To Pattern Recognition And Image Processing, World Scientific, 2002.
• [2] A. Ghosh and S. K. Pal: Neural network, self-organization and object extraction, Pattern recognition Letters, 13(5), 1992, 387-397.
• [3] A. Ghosh, N. R. Pal and S. K. Pal: Self-organization for object extraction using multilayer neural network and fuzziness measures, IEEE Transactions on Fuzzy Systems, 1, 1, 1993, 54-68.
• [4] A. Kandel: Fuzzy Mathematical Techniques with Applications, New York: Addison-Wesley, 1986.
• [5] A. K. Datta, S. Munshi and S. Bhattacharyya: Object Extraction In Artificial Retina Using Cellular Nenral Network Optimized By Genetic Algorithm With Fuzziness Measure,Proceedings of International Conference on Fiber Optics and Photonics, 2, 2000, 723-725.
• [6] A. Rosenfeld and A. C. Kak: Digital Picture Processing, New York: Academic Press, 1982.
• [7] D. T. Pham and E. J. Bayro-Corrochano: Neural computing for noise filtering, edge detection and signature extraction, Journal of Systems Engineering, 2, 2, 1998, 666-670.
• [8] D. W. Opitz and J. W. Shavlik: Using Genetic Search to Refine Knowledge-Based Neural Networks, Machine Learning: Proceedings of the Eleventh International Conference, W. Cohen and H. Hirsh, eds., Morgan Kaufmarm, San Fransisco, CA, 1994.
• [9] E. C. -K. Tsao, W. -C. Lin and C. -T. Chen: Constraint satisfaction neural networks for image recognition, Pattern Recognition, 26, 4, 1993, 553-567.
• [10] E. C. Paz: Pruning Neural Networks with Distribution Estimation Algorithms, GECCO 2003, 2003, 790-800.
• [11] G. F. Miller and P. M. Todd: Exploring adaptive agency in theory and methods for simulating the evolution of learning, Connectionist Models, Morgan Kauf-mann, 1990.
• [12] G. F. Miller, P. M. Todd and S. Hegde: Designing neural networks using genetic algorithms, Proceedings of the Third International Conference on Genetic Algorithms, Arlington, VA. Morgan Kaufmann, 1989, 379-384.
• [13] H. Kitano: Designing neural networks using genetic algorithms with graph generation system, Complex Systems, 4, 1990, 461-476.
• [14] H. Kitano: Empirical studies on the speed of convergence of neural network training using genetic algorithms. Proceedings of the Eleventh National Conference on Artificial Intelligence, Boston, MA. AAAI/MIT Press, 1990, 789-795.
• [15] J. S. Lim: Image Enhancement in Digital Image Processing Techniques (M. P. Ekstrom, ed.), New York, Academic Press, 1984.
• [16] K. Fukushima: Neocognitron: A self-organizing multilayer neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern., 36, 1980, 193-202.
• [17] L. A. Zadeh: Fuzzy Sets, Inform, and Control, 8, 1965, 338-353.
• [18] L. I. Perlovsky, W. H. Schoendor, B. J. Burdick et al.: Model-based nenral network for target detection in SAR images, IEEE Transactions on Image Processing, 6, 1, 1997, 203-216.
• [19] M. N. Nasrabadi and W. Li: Object recognition by a Hopfield neural network, IEEE Transactions on Systems, Man and Cybernetics, 21, 6, 1991, 1523-1535.
• [20] M. R. Banham and A. K. Katsaggelos: Digital Image Restoration, IEEE Signal Processing Magazine, 14, 2, 1997, 24-41.
• [21] N. Dodd: Optimization of network structure using genetic techniques, Proceedings oj IEEE International Joint Conference on Neural Networks, 3, Paris, 1990, 965-970.
• [22] P. G. Powell and B. E. Bayer: A Method for the Digital Enhancement of Un-sharp, Grainy Photographic Images, Proceedings of International Conference on Electronic Image Processing, IEEE, U. K., 1982, 179-183.
• [23] R. C. Gonzalez and R. E. Woods: Digital Image Processing, eds. 2, Pearson Ed., 2002.
• [24] S. A. Harp, T. Samad and A. Guha: Designing application-specific neural networks using the genetic algorithm, Advances in Neural Information Processing Systems, 2, D. Touretzky., eds., San Maeto, CA. Morgan Kaufmann, 447-454, 1989.
• [25] S. A. Harp, T. Samad and A. Guha: Towards a genetic synthesis of neural networks, Proceedings of Third International Conference on Genetic Algorithms, 1989.
• [26] S. Aniari: Mathematical theory of self-organization in neural nets, in Organization of Neural Networks: Structures and Models, W. V. Seelen, G. Shaw and U. M. Leinhos, eds., New York: Academic Press, 1988.
• [27] S. Bhattacharyya, P. Dutta and U. Maulik: Multi-Scale Object Extraction Using Self Organizing Neural Network With A Multi-Level Sigmoidal Activation Function, Proceedings of Fifth International Conference on Advances in Pattern Recognition, 2003, 435-438.
• [28] S. Ghosh and A. Ghosh: A GA-Fuzzy Approach to evolve Hopfield type optimum networks for object extraction, AFSS 2002, LNAI2275, N. R. Pal and M. Sugeno eds., Springer Verlag, Heidelberg, Berlin, 2002, 444-449.
• [29] S. Haykin: Neural networks: a comprehensive foundation, Macmillan College Publishing Co., New York, 1994.
• [30] S. Oliker, M. Furst and O. Maimon: A distributed genetic algorithm for neural network design and training. Complex Systems, 6, 459-477, 1992.
• [31] S. S. Young, P. D. Scott and N. M. Nasrabadi: Object recognition using multilayer Hopfield neural network, IEEE Transactions on Image Processing, 6, 3, 1997, 357-372.
• [32] T. J. Ross and T. Ross: Fuzzy Logic With Engineering Applications, McGraw hill College Div., 1995.
• [33] T. Kohonen: Self-organizing maps, Springer Series in Information Sciences, Springer Verlag, Berlin, 30, 1995.
• [34] T. S. Huang and G. Y. Tang: A Fast Two-Dimensional Median Filtering Algorithm, IEEE Transactions on Accoust. Speech, Signal Process., ASSP-27. 1979, 13-18.
• [35] W. Schiffmann, M. Joost and R. Werner: Synthesis and performance analysis of multilayer neural network architectures, Technical Report 16, University of Koblenz, Institute for Physics, 1992.