This Article 
 Bibliographic References 
 Add to: 
Selective and Focused Invariant Recognition Using Distributed Associative Memories (DAM)
August 1990 (vol. 12 no. 8)
pp. 809-814

A method of 2-D object recognition based on the Moore-Penrose distributed associative memory is presented. Using known relationships between DAMs and regression analysis, the selectivity of the association weights is improved in an iterative way be discarding from further consideration response vectors deemed to be insignificant. Such selectivity allow the system to focus on the significant associations and to reduce crosstalk effects. The same formalism that allows the significance of the association weights to be computed also provides for a reject option. Experiments incorporating the proposed method onto an invariant recognition system prove the feasibility and benefits of the recognition scheme.

[1] T. Kohonen,Self-Organization and Associative Memory. Berlin, Germany: Springer-Verlag, 1988, p. 132.
[2] J. Schürmann,Polynomklassifikatoren für die Zeichenerkennung. Vienna, Austria: Oldenburg München, 1977.
[3] H. Wechsler and G. L. Zimmerman, "2-D invariant object recognition using distributed associative memory,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, pp. 811-821, Nov. 1988.
[4] K. Murakami and T. Aibara, "An improvement on the Moore-Penrose generalized inverse associative memory,"IEEE Trans. Syst., Man, Cybern., vol. SMC-17, pp. 699-707, July/Aug. 1987.
[5] D. O. Hebb,The Organization of Behavior. New York: Wiley, 1949.
[6] S. Weisberg,Applied Linear Regression, 2nd ed. New York: Wiley, 1985.
[7] L. Massone, G. Sandini, and V. Tabliasco, "Form-invariant topological mapping strategy for 2D shape recognition,"Comput. Vision, Graphics, Image Processing, vol. 30, no. 1, pp. 169-188, 1985.
[8] R. A. Messner, "An image processing architecture for real time generation of scale and rotation invariant patterns,"Comput. Vision, Graphics, Image Processing, vol. 31, no. 1, pp. 50-66, 1985.
[9] W. Pölzleitner and H. Wechsler, "Invariant pattern recognition using associative memory," Joanneum Research, Inst. Digital Image Processing and Graphics, Tech. Rep. DIBAG-48, Mar. 1990.
[10] H. Wechsler and G. L. Zimmerman, "Distributed associative memories and bin-picking,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 814-822, 1989.
[11] W. Pölzleitner, "A Hough transform method to segment images of wooden boards," inProc. 8th Int. Conf. Pattern Recognition (ICPR), Paris, France, Oct. 1986, pp. 262-264.

Index Terms:
computerised pattern recognition; content addressable storage; 2-D object recognition; Moore-Penrose distributed associative memory; regression analysis; selectivity; association weights; computerised pattern recognition; content-addressable storage
W. Pölzleitner, H. Wechsler, "Selective and Focused Invariant Recognition Using Distributed Associative Memories (DAM)," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 809-814, Aug. 1990, doi:10.1109/34.57670
Usage of this product signifies your acceptance of the Terms of Use.