Efficient Object Extraction Using Fuzzy Cardinality Based Thresholding, Hopfield Network

An efficient technique that integrates the advantages of both fuzzy theory and Hopfield type neural network for object extraction from noisy background is proposed in this article. In the initial phase of the proposed technique, a fuzzy contrast enhancement of the input noisy object scene is carried out. Subsequently, the object scene is thresholded based on its fuzzy cardinality values to generate a smaller region of interest (ROI). Finally, a Hopfield network is used in the ROI to extract the object from the noisy background. Since the estimated ROI is lesser in size than the entire object scene, the Hopfield network required for the object extraction has a smaller network configuration. This in turn makes the object extraction process more efficient rather than the conventional approach where a fully connected network, with number of nodes equal to the number of pixels in the object scene, is used.

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[2]  Sankar K. Pal,et al.  Fuzzy Mathematical Approach to Pattern Recognition , 1986 .

[3]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[4]  Sankar K. Pal,et al.  Object Background Classification Using Hopfield Type Neural Network , 1992, Int. J. Pattern Recognit. Artif. Intell..

[5]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[6]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[7]  Sankar K. Pal,et al.  Designing Hopfield Type Networks Using Genetic Algorithms and Its Comparison with Simulated Annealing , 1997, Int. J. Pattern Recognit. Artif. Intell..

[8]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[9]  James C. Bezdek,et al.  Fuzzy Kohonen clustering networks , 1994, Pattern Recognit..

[10]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[11]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Terrance L. Huntsberger,et al.  PARALLEL SELF-ORGANIZING FEATURE MAPS FOR UNSUPERVISED PATTERN RECOGNITION , 1990 .

[13]  Chin-Teng Lin,et al.  Neural fuzzy systems , 1994 .

[14]  E. Dubois,et al.  Digital picture processing , 1985, Proceedings of the IEEE.

[15]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[16]  G. Kane.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[17]  Siddhartha Bhattacharyya,et al.  Photonic implementation of Hopfield neural network for associative pattern recognition , 2001, International Conference on Fiber Optics and Photonics.