This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Pictorial Information Retrieval Using the Random Neural Network
July 1992 (vol. 18 no. 7)
pp. 590-600

A technique is developed based on the use of a neural network model for performing information retrieval in a pictorial information system. The neural network provides autoassociative memory operation and allows the retrieval of stored symbolic images using erroneous or incomplete information as input. The network used is based on an adaptation of the random neural network model featuring positive and negative nodes and symmetrical behavior of positive and negative signals. The network architecture considered has hierarchical structure and allows two-level operation during learning and recall. An experimental software prototype, including an efficient graphical interface, has been implemented and tested. The performance of the system has been investigated through experiments under several schemes concerning storage and reconstruction of patterns. These schemes are either based on properties of the random network or constitute adaptations of known neural network techniques.

[1] Y. S. Abu-Mostafa and J. St. Jacques, "Information capacity of the Hopfield model,"IEEE Trans. Inform. Theory, vol. IT-31, pp. 461-464, 1985.
[2] S. V. B. Aiyer, M. Niranjan, and F. Fallside, "A theoretical investigation into the performance of the Hopfield model,"IEEE Trans. Neural Networks, vol. 1, pp. 204-215, June 1990.
[3] V. Atalay, E. Gelenbe, and N. Yalabik, "Texture generation with the random neural network model," inArtificial Neural Networks, Kohonenet al. Eds. Amsterdam: North-Holland, 1991, vol. 1, pp. 111-116.
[4] P. Baldi, "Neural networks, orientations of the hypercube, and algebraic threshold functions,"IEEE Trans. Inform. Theory, vol. 34, pp. 523-530, May 1988.
[5] F. Biennier, J. M. Pinon, and M. Guivarch, "A connectionist method to retrieve information in hyperdocuments," inProc. Int. Neural Network Conf., vol. 1, pp. 444-448, 1990.
[6] S. K. Chang, E. Jungert, S. Levialdi, T. Tortora, and T. Ichikawa, "An image processing language with icon-assisted navigation,"IEEE Trans. Software Engineering, vol. 11, pp. 811-819, Aug. 1985.
[7] S. -K. Chang and E. Jungert, "A spatial knowledge structure for image information systems using symbolic projections," inVisual Languages and Applications(T. Ichikawa, E. Jungert, and R. R. Korfhage, Eds.). New York: Plenum, 1990, pp. 277-303.
[8] S. K. Chang, Q. Y. Shi, and S. W. Yan, "Iconic indexing by 2-D strings,"IEEE Trans. Pattern. Anal. Machine Intell., vol. 9, pp. 484-492, July 1984.
[9] S. K. Chang, C. W. Yan, D. Dimitroff, and T. Arndt, "An intelligent image database system,"IEEE Trans. Software Engineering, vol. 14, pp. 681-688, May 1988.
[10] S. K. Chang, M. Tauber, B. Yu, and J. S. Yu, "A visual language compiler,"IEEE Trans. Software Engineering, vol. 15, pp. 506-525, May 1989.
[11] S. K. Chang, "A visual language compiler for information retrieval by visual reasoning,"IEEE Trans. Software Engineering, vol. 16, pp. 1136- 1149, Oct. 1990.
[12] A. Dembo, "On the capacity of associative memories with linear threshold functions,"IEEE Trans. Inform. Theory, vol. 35, pp. 709-720, July 1989.
[13] G. Fahner, "A neural net that manages a hierarchical spatial database," inArtificial Neural Networks, Kohonenet al.Eds. vol. 1, pp. 441-446, North-Holland, 1991.
[14] E. Gelenbe, "Random neural networks with negative and positive signals and product form solution,"Neural Computation, vol. 1, pp. 502-510, 1989.
[15] E. Gelenbe, "Stability of the random neural network model,"Neural Computation, vol. 2, pp. 239-247, 1990.
[16] E. Gelenbe, "Theory of the random neural network model," inNeural Networks: Advances and Applications. Amsterdam: North-Holland, 1991, pp. 1-20.
[17] E. Gelenbe, A. Stafylopatis, and A. Likas, "Associative memory operation of the random network model," inArtificial Neural Networks, Kohonenet al., Eds. Amsterdam: North-Holland, 1991, pp. 307-312.
[18] M. Gerso, "Information retrieval using self-organizing and heteroassociative supervised neural networks," inProc. Int. Neural Network Conf., vol. 1, pp. 361-364, 1990.
[19] A. Goodman, R. Haralick, and L. Shapiro, "Knowledge-based computer vision,"Computer, vol. 22, pp. 43-54, Dec. 1989.
[20] J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities,"Proc. Nat. Academy Sci., vol. 79, pp. 2554-2558, 1982.
[21] S. S. Iyengar and R. L. Kashyap, "Image databases,"IEEE Trans. Software Engineering, vol. 14, pp. 608-610, May 1988.
[22] T. Joseph and A. F. Cardenas, "PICQUERY: A high level language for pictorial database management,"IEEE Trans. Software Engineering, vol. 14, pp. 630-638, May 1988.
[23] Y. Kamp and M. Hasler,Recursive Neural Networks for Associative Memory, New York: Wiley, 1990.
[24] B. Kosko,Neural Networks for Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1992.
[25] A. Likas and A. Stafylopatis, "An investigation of the analogy between the random network and the Hopfield network," inProc. ISCIS VI, 1991.
[26] R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, "The capacity of the Hopfield associative memory,"IEEE Trans. Inform. Theory, vol. IT-33, pp. 461-482, 1987.
[27] M. Mokhtari, "Reconnaissance d'Images Typées par le Réseau Neuronal Aléatoire," inProc. Int. Colloq. Parallel Image Processing, June 1991.
[28] A. Motro, "Letter from the Editor,"Data Engineering, vol. 12, pp. 2-3, 1989.
[29] Y. H. Pao,Adaptive Pattern Recognition and Neutral Networks, Reading, MA: Addison-Wesley, 1989.
[30] S. S. Venkatesh and D. Psaltis, "Linear and logarithmic capacities in associative neural networks,"IEEE Trans. Inform. Theory, vol. 35, pp. 558-568, 1989.

Index Terms:
pictorial information retrieval; random neural network; autoassociative memory operation; stored symbolic images; hierarchical structure; learning; recall; software prototype; graphical interface; performance; random network; computerised picture processing; content-addressable storage; graphical user interfaces; information retrieval; neural nets; software prototyping
Citation:
A. Stafylopatis, A. Likas, "A Pictorial Information Retrieval Using the Random Neural Network," IEEE Transactions on Software Engineering, vol. 18, no. 7, pp. 590-600, July 1992, doi:10.1109/32.148477
Usage of this product signifies your acceptance of the Terms of Use.