This Article 
 Bibliographic References 
 Add to: 
Automatic Target Recognition Using a Neocognitron
April 1992 (vol. 4 no. 2)
pp. 167-172

The use of a neocognitron in an automatic target recognition (ATR) system is described. An image is acquired, edge detected, segmented, and centered on a log-spiral grid using subsystems not discussed in the paper. A conformal transformation is used to map the log-spiral grid to a computation plane in which rotations and scalings are transformed to displacements along the vertical and horizontal axes, respectively. Since the neocognitron can recognize shifted objects, the use of log-spiral images by the neocognitron enables the system to recognize scaled, rotated, and translated objects. Two modifications to prior neocognitron implementations are described. A new weight reinforcement method is introduced which solves a significant training problem for the neocognitron. A method of reducing training time is also introduced which specifies the initial layer of weights in the network. All subsequent layers are trained using unsupervised learning. Simulation results using 32*32 and 64*64 intercontinental ballistic missile (ICBM) images are presented.

[1] C. Hsin, R. M. Inigo, and E. S. McVey, "Image motion detection and estimation," inJoint SPIE-IECON Conf. Proc., Philadelphia, PA, Nov. 1989.
[2] G.S. Himes, R. M. Inigo, and C. Narathong, "VLSI implementable neural networks for target tracking," in S. Rogers, ed.,Applications of Artificial Neural Networks, Proc. SPIE, 1991, pp. 671-682.
[3] C. Braccini, G. Gambardella, G. Sandini, and V. Tagliasco, "A model of the early stages of the human visual system: Functional and topological transformations performed in the peripheral visual Field,"Biol. Cybern.vol. 44, pp. 47-58, 1982.
[4] R. A. Messner and H. H. Szu, "AnN2parallel architecture for real time scale/rotational invariant image processing,"Comput. Vision, Graph., Image Processing, vol. 31, pp. 50-66, 1985.
[5] C. F. R. Wiman and G. Chaikin, "Logarithmic spiral grids for image processing and display,"Comput. Graph. Image Processing, vol. 11, pp. 197-226, 1979.
[6] K. Fukushima, "Cognitron: A self-organizing multilayered neural network,"Biol. Cybern., vol. 20, pp. 121-136, 1975.
[7] K. Fukushima and S. Miyake, "Neocognitron: Self-organizing network capable of position-invariant recognition of patterns," inProc. 5th Int. Conf. Pattern Recognition, vol. 1, pp. 459-461, 1980.
[8] K. Fukushima and S. Miyake, "Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position,"Pattern Recognition, vol. 15, no. 6, pp. 455-469, 1982.
[9] D. H. Hubel and T. N. Wiesel, "Receptive fields, binocular interaction, and funtional architecture in the cat's visual cortex,"J. Physiol., vol. 160, pp. 106-154, 1962.
[10] S.A. Solla, "Learning and generalization in layered neural networks: The contiguity problem," inNeural Networks from Models to Applications, L. Personnes and G. Dreyfus, Eds., I.D.S.E.T., Paris, 1989, pp. 168-177.
[11] Y. Le Cun, "Generalization and Network Design Strategies,"Connectionism in Perspective, R. Pfeifer, Z. Schreter, F. Fogelman, and L. Steels, Eds. Zurich: Elsevier, 1989.
[12] K. Fukushima, S. Miyake, and T. Ito, "Neocognitron: A neural network model for a mechanism of visual pattern recognition,"IEEE Trans. Syst., Man, Cybern., vol. SMC-13, Sept./Oct. 1983.
[13] D. Kirk and D. Voorhies, "The Rendering Architecture of the DN10000VS,"Computer Graphics(Proc. Siggraph), Vol. 24, No. 4, Aug. 1990, pp. 299-307.
[14] M. Menon and K. Heinemann, "Classification of patterns using a self-organizing neural network,"Neural Networks, vol. 1, pp. 201-215, 1988.

Index Terms:
neocognitron; automatic target recognition; conformal transformation; log-spiral grid; computation plane; weight reinforcement method; training problem; unsupervised learning; intercontinental ballistic missile; computerised pattern recognition; computerised picture processing; learning systems; military systems; neural nets
G.S. Himes, R.M. Iñigo, "Automatic Target Recognition Using a Neocognitron," IEEE Transactions on Knowledge and Data Engineering, vol. 4, no. 2, pp. 167-172, April 1992, doi:10.1109/69.134254
Usage of this product signifies your acceptance of the Terms of Use.