Self organizing neural network (SONN) based gray scale object extractor with a multilevel sigmoidal (MUSIG) activation function

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

Abstrakty

EN

A single three layer self organizing neural network, characterized by the standard bilevel sigmoidal activation function, is efficient in extraction of binary objects from a noisy image by means of self supervision. A multilevel version of the generalized sigmoidal activation function for mapping multiscale input information into multiple scales of gray, is introduced in this article. The multilevel function is used to induce multiscaling capability in a single three layer self organizing neural network. An application of the proposed multilevel activation function for the extraction of multiscale images, is demonstrated using a synthetic and two real life multiscale images. Experiments have been conducted with different combinations of parameters of the function. The standard correlation factors between the extracted and the original images indicate the efficiency of the proposed multilevel activation function.

Słowa kluczowe

EN

multiscale object extraction; self-organizing neural network; multilevel activation function

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2008
• Tom: Vol. 33, No. 2
• Strony: 131--165
• Opis fizyczny: Bibliogr. 51 poz.

Twórcy

autor

Bhattacharyya S.

autor

Dutta P.

autor

Maulik U.

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

Bibliografia

• [1]Amari S., Mathematical theory of self-organization in neural nets, in: W. V. Seelen, G. Shaw and U. M. Leinhos (eds.), Organization of Neural Networks: Structures and Models, New York: Academic Press, 1988.
• [2]Anderson J. A., Introduction to Neural Networks, MIT Press, Cambridge, MA, 1995.
• [3]Baccar M., Gee L. A., Abidi M. A., Gonzalez R. C., Segmentation of Range Images via Data Fusion and Morphological Watersheds, Pattern Recognition, 29, 10, 1996, 1671-1685.
• [4]Bhattacharyya S., Dutta P., Designing pruned neighborhood neural networks for object extraction from noisy background, Journal of Foundations of Computing and Decision Sciences, 31, 2, 2006, 105-134.
• [5]Bhattacharyya S., Dutta P., Maulik U., Multi-scale object extraction using self organizing neural network with a multi-level sigmoidal activation function, Proceedings of the Fifth International Conference on Advances in Pattern Recognition,2003,435-438.
• [6]Bhattacharyya S., Dutta P., DuttaMajumder D., Multiscale object extraction using a self organizing neural network with multilevel beta activation function and its sigmoidal counterpart: A comparative study, Proceedings of the International Conference on Recent Trends and New Directions of Research in Cybernetics and Systems Theory, 2004.
• [7]Dutta P., Bhattacharyya S., Dasgupta K., Multi-scale object extraction using a self organizing neural network with a multi-level beta activation function, Proceedings of the International Conference on Intelligent Sensing and Information Processing, 2004, 139-142.
• [8]Boskovitz V., Guterman H., An adaptive neuro-fuzzy system for automatic image segmentation and edge detection, IEEE Transactions on Fuzzy Systems, 10, 2, 2002, 247-262.
• [9]Carpenter G., Neural network models for pattern recognition and associative memory, Neural Networks, 2, 4, 1989, 243-258.
• [10]Choi S -H., Rockett P., The training of Neural Classifiers with Condensed Datasets, IEEE Transactions on Systems, Man and Cybernetics, Part B, 32, 2, 2002, 202-206.
• [11]Chow C. K., Kaneko T., Automatic Boundary Detection of the Left Ventricle from Cineangiograms, Comp., and Biomed. Res., 5, 1972, 388-410.
• [12]Datta A. K., Munshi S., Bhattacharyya S., Object Extraction In Artificial Retina Using Cellular Neural Network Optimized By Genetic Algorithm With Fuzziness Measure, Proceedings of International Conference on Fiber Optics and Photonics, 2, 2000, 723-725.
• [13]Deshmukh K. S., Shinde G. N., An adaptive color image segmentation, Electronic Letters on Computer Vision and Image Analysis, 5, 4, 2005, 12-23.
• [14]Dodd N., Optimization of network structure using genetic techniques, Proceedings of IEEE International Joint Conference on Neural Networks, 3, 1990, 965-970.
• [15]Duda R. O., Hart P. E., Pattern Classification and Scene Analysis, Wiley, NY, 1973.
• [16]Egmont-Petersen M., Ridder D. de, Handels H., Image processing using neural networks - a review, Pattern Recognition, 35, 10, 2002, 2279-2301.
• [17]Forrest B. M., et al: Neural network models, Parallel Computing, 8, 1988, 71-83.
• [18]Fu K. S., Mui J. K., A Survey of Image Segmentation, Pattern Recognition, 13, 1, 1981, 3-16.
• [19]Ghosh A., Pal N. R., Pal S. K., Self-organization for object extraction using a multilayer neural network and fuzziness measures, IEEE Transactions on Fuzzy Systems, 1, 1, 1993, 54-68.
• [20]Ghosh A., Sen A., Soft Computing Approach To Pattern Recognition And Image Processing, World Scientific, 2002.
• [21]Glauber R. J., Time-dependent statistics of the Ising model, Journal of Mathematical Physics, 4, 1963, 294-307.
• [22]Gonzalez R. C., Woods R. E., Digital Image Processing, 2nd ed., Pearson Ed., 2002.
• [23]Haddon J. F., Boyce J. F., Image Segmentation by Unifying Region and Boundary Information, IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 10, 1990, 929-948.
• [24]Harp S. A., Samad T., Guha A., Designing application-specific neural networks using the genetic algorithm, in: D. Touretzky (eds.), Advances in Neural Information Processing Systems, 2, San Maeto, CA. Morgan Kaufmann, 1989, 447-454.
• [25]Harp S. A., Samad T., Guha A., Towards a genetic synthesis of neural networks, Proceedings of the Third International Conference on Genetic Algorithms, 1989.
• [26]Haykin S., Neural Networks: A Comprehensive Foundation, 2nd. ed., Prentice Hall, Upper Saddle River, NJ, 1999.
• [27]Hornik K., Approximation capabilities of multilayer feedforward networks, Neural Networks, 4, 2, 1991, 251-257.
• [28]Jain A. K., Duin R. P. W., Mao J., Statistical pattern recognition: a review, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 1, 2000, 4-37.
• [29]Kamgar-Parsi B., Automatic Target Extraction in Infrared Images, NRL Rev., 1995, 143-146.
• [30]Karayiannis N. B., Purushothaman G., Fuzzy pattern classification using feedforward neural networks with multilevel hidden neurons, IEEE World Congress on Computational Intelligence, 3, 1994, 1577-1582.
• [31]Kasamov N., Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering, MIT Press, Cambridge, MA, 1996.
• [32]Koch C., Biophysics of Computation: Information Processing in Single Neurons,Oxford university Press, NY, 1999.
• [33]Kosko B., Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall, Englewood Cliffs, NJ, 1992.
• [34]Leondes C. T., Neural Network Techniques and Applications, in: Image Processing and Pattern Recognition, Academic Press, 1998.
• [35]Lippmann R. P., An introduction to computing with neural nets, IEEE ASSP Magazine, 1987, 3-22.
• [36]Lippmann R. P., Pattern classification using neural networks, IEEE Communications Magazine, 27, 1989, 47-64.
• [37]Maass W., Bishop C. M. (eds.), Pulsed Neural Networks, MIT Press, Cambridge, MA, 1999.
• [38]McCulloch W. S., Pitts W., A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 5, 1943, 115-133.
• [39]Oliker S., Furst M., Maimon O., A distributed genetic algorithm for neural network design and training, Complex Systems, 6, 1992, 459-477.
• [40]Opitz D. W., Shavlik J. W., Using Genetic Search to Refine Knowledge-Based Neural Networks, in: W. Cohen and H. Hirsh (eds.), Machine Learning: Proceedings of the Eleventh International Conference, Morgan Kaufmann, San Fransisco, CA, 1994.
• [41]Pavlidis T., Liow Y. T., Integrating Region Growing and Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 3, 1990, 225-233.
• [42]Paz E. C., Pruning Neural Networks with Distribution Estimation Algorithms, GECCO 2003, 2003, 790-800.
• [43]Reed R., Pruning algorithms - A survey, IEEE Transactions on Neural Networks, 4, 5, 1993, 740-747.
• [44]Ross T. J., Ross T., Fuzzy Logic With Engineering Applications, McGraw Hill College Div., 1995.
• [45]Roth M. W., Survey of Neural Network Technology for Automatic Target Recognition, IEEE Transactions on Neural Networks, 1, 1, 1990, 28-43.
• [46]Si J., Michel A. N., Analysis and synthesis of discrete-time neural networks with multi-level threshold functions, Proceedings of the IEEE International Symposium on Circuits, 1991.
• [47]Tou J. T., Gonzalez R. C., Pattern Recognition Principles, Reading MA: Addison Wesley, 1974.
• [48]Wah B., Lowrie M., Li G. -J., Computers for symbolic processing, Proceedings of IEEE, 4,1989.
• [49]Young S. S., Scott P. D., Nasrabadi N. M., Object recognition using multilayer Hopfield neural network, IEEE Transactions on Image Processing, 6, 3, 1997, 357-372.
• [50]Zadeh L. A., Fuzzy Sets, Information and Control, 8, 1965, 338-353.
• [51]Zhang G. P., Neural networks for classification: a survey, IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, 30, 4, 2000, 451-462.