A bi-stage neuro - fuzzy classifier system for object identification

• Autorzy: Pantazopoulos D. P. , Tzafestas S. G.
• Języki publikacji: EN

Abstrakty

EN

In this paper a two-stage hybrid system for object recognition, that is needed in artificial vision applications, is presented. For the description of the images, three features, namely geometrical parameters, moments, and internal angles, are used as inputs to the classifier. The first stage of the system consists of three neural classifiers (one for each feature). In the second stage the outputs of the first stage are presented to a fuzzy reasoning system which acts as the final classifier and makes the final decision. The proposed bi-stage hybrid neuro-fuzzy classifier (symbolically bisNFC) was tested with a large set of images. The results and the comparisons with other methods showed that bisNFC is a promising classification system.

Słowa kluczowe

EN

object recognition; neural networks; fuzzy logic; classification system; hybrid; object identification

PL

sieć neuronowa; logika rozmyta; identyfikacja obiektu

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2007
• Tom: Vol. 12, no 1
• Strony: 53--65
• Opis fizyczny: Bibliogr. 29 poz., rys.

Twórcy

autor

Pantazopoulos D. P.

autor

Tzafestas S. G.

• School of Electrical and Computer Engineering, National Technical University of Athens, Zographai, Athens, Greece, Grl5573.,

Bibliografia

• [1] T. Pavlidis; Structural Pattern Recognition, Springer, 1977
• [2] F. Holderman, M Bohner , B Bargel and H Kazmierczak 1976. Review of image processing, Proceedings of ISPRS Congress, Helsinki.
• [3] D. A. Mitzias, and Basil G. Mertzios. A Neural Multiclassifier System for Object Recognition in Robotic Vision Applications. ScienceDirect 36, 3-4 (October-December 2004):315-330.
• [4] Dasarathy B., Data mining tasks and methods: Classification: nearest-neighbor approaches, Oxford University Press, Inc., New York, NY, USA, 2002
• [5] D.S. Broomhead, D. Lowe, Multivariable functional interpolation and adaptative networks, Complex Systems, 2(1988) 321-355.
• [6] J.F. Baldwin, J. Lawry, T.P. Martin, A mass assignment based ID3 algorithm for decision tree induction, Internat. J. Intell. Systems, 12 (1997) 523-552.
• [7] C.Z. Janikow, A genetic algorithm for optimizing fuzzy decision trees, Inform. Sci., 89 (1996) 275-296.
• [8] Chen, Shy-Shyan; Shih, Frank Y.; NG, Peter A. A fuzzy model for unsupervised character classification, Inf. Sci., Appl. 2, No.3.
• [9] P. Billaudel, A. Devillez, G. Villermain Lecolier, Performance evaluation of fuzzy classification methods designed for real time application, Internat. J. Approx. Reason., 20 (1999) 1-20.
• [10] O. Gascuel, et al., Twelve numerical, symbolic and hybrid supervised classification methods, Internat. J. Pattern Recognition Artif. Intell., 12 (5) (1998) 517-571.
• [11] M.E. Cohen, D.L. Hudson, Integration of neural network techniques with approximate reasoning in knowledge based systems, in: A. Kandel, G. Langholz (Eds.), Hybrid Architectures for Intelligent Systems, CRC Press, Boca Raton, FL, 1992, pp. 72-85.
• [12] H. Takagi, Fusion technology of fuzzy theory and neural network: survey and future directions, in: Proc. Intemat. Conf. on Fuzzy Logic and Neural Networks, Iizuka, 1990, pp. 13-26.
• [13] H. Takagi, I. Hayashi, Artificial neural network driven fuzzy reasoning, Internal. J. Approx. Reasoning, 5 (1991) 191-212.
• [14] Mohammad-Taghi Vakil-Baghmisheh, Nikola Pavesic, A fast simplified fuzzy ARTMAP network, Neural processing letters 17:33, 273-316, Kluwer, 2003
• [15] P.E. Utgoff, Perceptron trees: A case study in hybrid concept representation, in: AAAI-88: Proc. 7th Natl. Conf. on Artificial Intelligence, Morgan-Kaufmann, San Mateo, CA, 1988, pp. 601-606.
• [16] RC Gonzalez and P. Wintz, Digital Image Processing, Addison-Wesley, Reading, MA, second edition, 1987.
• [17] I. M. Spiliotis, B. G. Mertzios: Fast algorithms for basic processing and analysis operations on block-represented binary images, Pattern Recognition Letters, 17(14): 1437-1450 (1996)
• [18] Dimitris A. Mitzias, Basil G. Mertzios: Shape recognition with a neural classifier based on a fast polygon approximation technique, Pattern Recognition, 27(5): 627-636 (1994)
• [19] S.J. Symons, R.G Fulcher., 1988a. Determination of wheat kernel morphological variation by digital analysis, J. Cereal Sci., 8, 211-218.
• [20] B. Gabrys and A. Bargiela, General Fuzzy Min-Max Neural Network for Clustering and Classification, IEEE Trans. on Neural Networks, vol. 11, no. 3, 2000, pp. 769-783
• [21] S.U. Salzberg, Learning with Nested Generalized Exemplars, Kluwer Academic, Hingham, MA, 1990.
• [22] R. Setiono, Feedforward neural network construction using cross validation, Neural Computation, 13 (2001) 2865-2877.
• [23] H. Ishibuchi and T. Nakashima, Voting in fuzzy rule-based systems for pattern classification problems, Fuzzy Sets and Systems, vol. 103, pp. 223-238, 1999.
• [24] J. Klir, St. Clair, Bo Yua, Fuzzy Set Theory: Foundations and Applications, Prentice Hall PTR; 1st edition (April 17, 1997)
• [25] T.K. Ho, A theory of multiple classifier systems and its application to visual word recognition, Ph.D. Thesis, University of Buffalo, 1992.
• [26] S.G Tzafestas and Y. Anthopoulos, Supervised learning in multilayer perceptrons : The back-propagation algorithm, in S.G Tzafestas (ed.), Soft Computing in Systems and Control Technology, World Scientific, Singapore/London, pp. 3-30, 1999
• [27] S. G. Tzafestas and Sot. Raptis, Fuzzy image processing: A review and comparison of methods, Image Processing and Communications, Vol. 5, Nol, pp. 3-24, 1999.
• [28] S. G Tzafestas and K. C. Zikidis, NeuroFast : An on-line neuro-fuzzy Art-based structure and parameter learning Takagi - Sugeno Kong Model, IEEE Trans, on Systems, Man and Cybernetics - Part B: Cybernetics, Vol. 31, No 5, pp 797-802, 2001
• [29] E. Skoundrianos and S.G Tzafestas, Modelling and fault detection/identification of dynamical discrete-time systems using MLP and a new sigmoid activation function, J. Intell. and Robotic Systems, vol. 41, No. l, pp 65-84, 2004.