Skip to main content
SpringerLink
Log in

The “Rubber-Mask” Technique-II, Pattern Storage and Recognition

  • Chapter
Learning Systems and Intelligent Robots

  • 116 Accesses

Abstract

This paper briefly summarizes much of the work in pattern recognition to date, and relates the rubber mask technique to previous work. A scheme for incorporating flexible-mask methods into a proposed pattern recognition and memory system is presented. A discussion based on some facts and on some conjecture of the human eye/brain system and how it recognizes patterns, possibly by flexible matching, is also presented.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. B. Widrow, “The rubber mask” technique I: Pattern measurement and analysis,” Pattern Recognition 5, 175–197 (1973).

    Article  Google Scholar 

  2. C.J.W. Mason, “Pattern Recognition Bibliography”, IEEE Systems, Man, and Cybernetics, Group Newsletter, October 1970, December 1970, February 1971, June 1971.

    Google Scholar 

  3. R.L. Gregory, “Eye and Brain: The Psychology of Seeing”, World University Library. McGraw-Hill, New York (1966).

    Google Scholar 

  4. Police identification kits are manufactured by the Identi-Kit Company which claims for its product in an advertisement on page 39 of Law and Order, September 1972:…It allows you to go to the witness or victim of a crime and develop a composite facial likeness of a suspect within minutes. Manual overlay of six to nine facial components becomes a complete line drawing without the use of complicated machines, photographs or the services of an artist. Also, Identi-Kit composites are easily reproduced and automatically code themselves for instant transmission to other Identi-Kit users all over the world….

    Google Scholar 

  5. B. Julesz, Foundations of Cyclopean Perception. University of Chicago Press, Chicago (1971).

    Google Scholar 

  6. Plato’s Republic, Book VI, Jowett Translation, Random House, Vintage Paperbacks.

    Google Scholar 

Adaline/Madaline

  1. B. Widrow and M.E. HOFF, “Adaptive switching circuits”, WESCON Convention Ree., Institute of Radio Engineers, N.Y. Pt. 4, pp. 96–104 (1960).

    Google Scholar 

  2. B. Widrow, “Generalization and information storage in networks of Adaline ‘neurons’,” Self Organizing Systems, M.C. Yovitz, G.T. Jacobi and G.D. Goldstein (eds) pp. 435–461. Spartan, Washington, D.C. 1962.

    Google Scholar 

  3. K. Steinbuch and B. Widrow, “A critical comparison of two kinds of adaptive classification networks”, IEEE Trans. Electronic Computers EC-14 (5), 737–740 (1965)

    Article  Google Scholar 

  4. J.S. Koford and G.F. Groner, “The use of an adaptive threshold element to design a linear optimal pattern classifier,”IEEE Trans. Information Theory IT-12, 42–50 (1966)

    Article  Google Scholar 

  5. C.H. Mays, “Effects of adaptation parameters on convergence time and tolerance for adaptive threshold elements”, IEEE Trans. Electronic Computers (short notes) EC-13, 465–468 (1964).

    Article  Google Scholar 

  6. N.J. Nilsson, Learning Machines. McGraw-Hill, New York (1965).

    Google Scholar 

  7. B. Widrow et al., “Adaptive antenna systems,” Proc. IEEE 55, 2143–2159 (1967).

    Article  Google Scholar 

Perceptron

  1. F. Rosenblatt, “The perceptron, a theory of statistical separability in cognitive systems”, Report VG-1196-G-1, Cornell Aeronautical Lab., Buffalo, New York (1958).

    Google Scholar 

  2. F. Rosenblatt, Principles of Neurodynamics, and the Theory of Brain Mechanisms. Spartan Books, Washington, P.C. (1962).

    Google Scholar 

  3. H.P. Block, “The perceptron: A model for brain functioning”. I, Rev. Mod. Phys. 34 (1), 123–135 (1962).

    Article  Google Scholar 

  4. H.P. Block, B.W. Knight and F. Rosenblatt, “Analysis of a four- layer series-coupled perceptron.” II, Rev. Mod. Phys. 34 (1), 135–142 (1962).

    Article  Google Scholar 

  5. N.J. Nilsson, Learning Machines. McGraw-Hill, New York (1965).

    Google Scholar 

  6. G. Nagy, “The state of art in pattern recognition”, Proc. IEEE 56 (5), 836–862 (1968).

    Article  Google Scholar 

  7. M.L. Minsky and S. Papert, Perceptrons: an Introduction to Computational Geometry. M.I.T. Press, Cambridge, Mass. (1969).

    Google Scholar 

Matched Filters and Learning Matrices

  1. “Matched filter issue”, IRE Trans. Information Theory IT-6, 309–417 (1960).

    Google Scholar 

  2. T. KaiLath, “Adaptive matched filters”, Mathematical Optimization Techniques, R. Bellman (ed), pp. 109–140. University of California Press (1963).

    Google Scholar 

  3. K. Steinbuch and U.A.W. Piske, “Learning matrices and their applications”, IEEE Trans. Electronic Computers EC-12 (5), 846–862 (1963).

    Article  Google Scholar 

  4. H. Kazmierczak and K. Steinbuch, “Adaptive systems in pattern recognition,” IEEE Trans. Electronic Computers EC-12 (5), 822–835 (1963).

    Article  Google Scholar 

Linear and Polynomial Discriminants

  1. W.H. Highleyman, “Linear decision functions, with application to pattern recognition”, Proc. IRE 50, 1501–1514 (1962).

    Article  Google Scholar 

  2. T.W. Anderson, Introduction to Multivariate Statistical Analysis. Wiley, New York (1965).

    Google Scholar 

  3. J.S. Koford and G.F. Groner,”The use of an adaptive threshold element to design a linear optimal pattern classifier”, IEEE Trans. Information Theory IT-12, 42–50 (1966).

    Article  Google Scholar 

  4. D. F. Specht, “Generation of polynomial discriminant-functions for pattern recognition”, IEEE Trans. Electronic Computers EC-16 (1), 308–319 (1967).

    Article  Google Scholar 

  5. D.F. Specht, “Vectorcardiographic diagnosis using the polynomial discriminant method of pattern recognition”, IEEE Trans. Biomedical Electronics BME-14 (2), 90–95 (1967)

    Article  Google Scholar 

Nearest Neighbour Rules

  1. T.M. Cover and P. E. Hart, “Nearest neighbor pattern classification”, IEEE Trans. Information Theory IT-13 (1), 21–27 (1967).

    Article  Google Scholar 

  2. T.M. Cover, “Estimation by the nearest neighbor rule”, IEEE Trans. Information Theory IT-14 (1), 50–55 (1968).

    Article  Google Scholar 

Integral Geomatry

  1. L.A. Santalo, Introduction to Integral Geometry. Hermann, Paris (1953).

    Google Scholar 

  2. A.B.J. Novikoff, “Integral geometry as a tool in pattern perception”, Principles of Self-Organization, Von FORESTER and Zopf (eds), pp. 347–368, Pergamon, Oxford (1962).

    Google Scholar 

  3. G. Tenery, “Pattern recognition function of integral geometry”, IEEE Trans. Military Electronics MIL-7, 196–199 (1963).

    Article  Google Scholar 

  4. E. Wong and J.A. Steppe, “Invariant recognition of geometrical shapes”, Methodologies of Pattern Recognition, S. Watanabe (ed), pp. 535–543. Academic, New York (1969).

    Google Scholar 

Pattern Classification by Clustering/Learning without a teacher

  1. F. Mosteller, “On pooling data”, J. Am. Stat. Assoc. 43 (242), 231–242 (1948).

    Article  Google Scholar 

  2. T.T. Tanimoto and D.J. Rogers, “A computer program for classifying plants”, Science 132 (3434), 1115–1118 (1960).

    Article  Google Scholar 

  3. D.B. Cooper and P.W. Cooper, “Nonsupervised adaptive signal detection and pattern recognition”, Inform. Control 7 (3), 416–444 (1964).

    Article  Google Scholar 

  4. R.E. Bonner, “On some clustering techniques”, IBM J. Res. Dev. 8 (1), 22–32 (1964).

    Article  Google Scholar 

  5. R.L. Mattson and J.E. Dammann, “A technique for determining and coding subclasses in pattern recognition problems”, IBM J. Res. Dev. 9 (4), 294–302 (1965).

    Article  Google Scholar 

  6. G.H. Ball and D.J. Hall, “Isodata, a novel method of data analysis and pattern classification”, Stanford Research Institute, Menlo Park, Calif. (April 1965).

    Google Scholar 

  7. J. Spragins, “Learning without a teacher”, IEEE Trans. Information Theory IT-12 (2), 223–230 (1966).

    Article  Google Scholar 

  8. S.C. Fralick, “Learning to recognize patterns without a teacher”, IEEE Trans. Information Theory IT-13 (1), 57–64 (1967).

    Article  Google Scholar 

  9. W.C. Miller, “A modified mean square error criterion for use in unsupervised learning”, Stanford Electronics Laboratories, Stanford, Calif., Tech. Rept. SEL-67–066 (TR 6778–2) (August 1967).

    Google Scholar 

  10. YA.Z. Tsypkin, “Self learning—what is it?” IEEE Trans. Automatic Control AC13 (6), 608–612 (1968).

    Article  Google Scholar 

  11. C.G. Hilborn, Jr. and D.G. Lainiotis, “Unsupervised learning minimum risk pattern classification for dependent hypotheses and dependent measurements”, IEEE Trans. Systems Science and Cybernetics SSC-5 (2), 109–115 (1969).

    Article  Google Scholar 

  12. A.N. Mucciardi and E.E. Gose, “An automatic algorithm and its properties in high-dimensional spaces,” IEEE Trans. Systems, Man and Cybernetics SMC-2 (2), 247–254 (1972).

    Article  Google Scholar 

Linguistic Approach to Pattern Recognition

  1. R.A. Kirsch, “Computer interpretation of English text and picture patterns”, IEEE Trans. Electronic Computers EC-13, 363–376 (1964).

    Article  Google Scholar 

  2. R.S. Ledley, “High-speed automatic analysis of biomedical pictures”, Science 146, 216–223 (1964).

    Article  Google Scholar 

  3. N. Chomsky, Aspects of the Theory of Syntax. M.I.T. Press (1965).

    Google Scholar 

  4. R. Narasimhan, “Syntax-directed interpretation of classes of pictures”, Comm. ACM 9, 166–173 (1966).

    Article  Google Scholar 

  5. M.B. Clowes, “Transformational grammars and the organization of pictures”, Automatic Interpretation and Classification of Images, A. Grasselli (ed), pp. 43–76. Academic, New York (1969).

    Google Scholar 

  6. R. Narasimhan, “On the description, generation, and recognition of classes of pictures”, Automatic Interpretation and Classification of Images, A. Grasselli (ed), pp. 1–41. Academic, New York (1969).

    Google Scholar 

  7. M. Eden, “Handwriting generation and recognition”, Recognizing Patterns, P.A. Kolers and M. Eden (eds) pp. 138–154. M.I.T. Press, Cambridge, Mass. (1968).

    Google Scholar 

  8. W.F. Miller and A.C. Shaw,”Linguistic methods in picture processing—a survey”, Fall Joint-Computer Conference, pp. 279–290 (December 1968).

    Google Scholar 

  9. A. Rosenfeld, “Chapter on picture description and picture languages,” Picture Processing by Computer, pp. 167–184. Academic, New York (1969).

    Google Scholar 

  10. J. Hopcroft and J. Ullman, Formal Languages and their Relation to Automata. Addison-Wesley, Reading, Mass. (1969).

    Google Scholar 

  11. A.C. Shaw, “Parsing of graph-representable pictures”; J. ACM 17 (3), 453–481 (1970).

    Article  Google Scholar 

  12. H.C. Lee and K.S. FU, “A stochastic syntax analysis procedure and its application to pattern recognition,” IEEE Trans. Comp., (July 1972).

    Google Scholar 

  13. “Special Issue on Syntactic Pattern Recognition”, Pattern Recognition 4, No. 1 (January 1972).

    Google Scholar 

Fingerprint Recognition

  1. William DIENSTEIN, Technics for the Crime Investigator. Charles C. Thomas (1952).

    Google Scholar 

  2. A. Grasselli, “On the automatic classification of fingerprints”, Methodologies of Pattern Recognition, S. Watanabe (ed.), pp. 253–315. Academic, New York (1969).

    Google Scholar 

  3. L.S. Penrose, “Dermatoglyphics”, Scient, Am. pp. 72–84 (December 1969).

    Google Scholar 

  4. “Proc. 1st and 2nd Natl. Symp. Law Enforcement Science and Technology” Thompson/Academic Press and IITRI. Articles

    Google Scholar 

  5. John E. GAFFNEY, JR. et al., “Fingerprint encoding and matching procedures for automated recognition systems”

    Google Scholar 

  6. C.B. Shelman, “Machine extraction of ridge endings from a noisy fingerprint”, pp. 409–416.

    Google Scholar 

  7. Vincent V. Horvath and Charles D. Doyle, “Recent developments in fingerprint recognition using coherent optical processing”, pp. 417–426.

    Google Scholar 

  8. Bernard M. Van Emden, “Advanced computer based fingerprint automatic classification technique” (FACT), pp. 493–505.

    Google Scholar 

  9. M.D. Freedman and E.D. Hietanen, “Application of parallel neighborhood logic to fingerprint processing”, pp. 507–509.

    Google Scholar 

  10. Richard W. Schwartz, “System considerations in automated fingerprint classification”, pp. 511–515.

    Google Scholar 

Human Vision

  1. R.L. Gregory, Eye and Brain, the Psychology of Seeing. World University Library, McGraw-Hill, New York (1966).

    Google Scholar 

  2. E.R. Hilgard and G.H. Bower, Theoriesof Learning, 3rd ed. Appleton-Century-Crofts, New York (1966).

    Google Scholar 

  3. P.C. Dodwell, Visual Pattern Recognition. Holt, Rinehart and Winston, New York (1970).

    Google Scholar 

  4. T.N. Cornsweet, “Measuring movements of the retinal image with respect to the retina”, Biomedical Sciences Instrumentation, W.E. Murray and P.F. Salisbury (ed), vol. 2. Plenum, New York (1964).

    Google Scholar 

  5. N.H. Mackworth, “A stand camera for line-of-night recording”, Perception and Psychophysics 2 (1967).

    Google Scholar 

  6. N.H. Mackworth and J.S. Bruner, “How adults and children search and recognize pictures”, Human Development 13, 149–177 (1970).

    Article  Google Scholar 

Books on Pattern Recognition

  1. G.L. Fischer, Jr., D.K. Pollock, B. Radack and M.E. Stevens (eds), Optical Character Recognition. Spartan Books, Washington (1962).

    Google Scholar 

  2. G. Sebestyen, Decision-Making Process in Pattern Recognition. Macmillan, New York (1962).

    Google Scholar 

  3. D.K. Pollock, C.J. Koester and J.T. Tippett, Optical Processing of Information. Spartan Books, Washington, D.C. (1963).

    Google Scholar 

  4. N.J. Nilsson, Learning Machines. McGraw-Hill, New York (1965).

    Google Scholar 

  5. L. Uhr, Pattern Recognition. Wiley, New York (1966).

    Google Scholar 

  6. K.S. Fu, Sequential Methods in Pattern Recognition and Machine Learning. Academic, New York (1968).

    Google Scholar 

  7. L.N. Kanal (ed), Pattern Recognition. Thompson, Washington (1968).

    Google Scholar 

  8. A. Rosenfeld, Picture Processing by Computer. Academic, New York (1969).

    Google Scholar 

  9. M.S. Watanabe, Methodologies of Pattern Recognition. Academic, New York (1969).

    Google Scholar 

  10. A. Grasselli (ed), Automatic Interpretation and Classification of Images. Academic, New York (1969).

    Google Scholar 

  11. J. Mendel and K. S. Fu, Adaptive Learnings and Pattern Recognition: Theory and Applications. Academic, New York (1970).

    Google Scholar 

  12. N. Bongard, Pattern Recognition. Spartan Books, New York (1970).

    Google Scholar 

  13. YA. Z. Tsypkin, Adaptation and Learning in Automatic Systems. Academic, New York (1971).

    Google Scholar 

  14. K.S. Fu (ed) Pattern Recognition and Machine Learning. Plenum, New York (1971).

    Google Scholar 

  15. O. Grusser and R. Klinke (eds), Pattern Recognition in Biological and Technical Systems. Springer, Berlin, New York(1971).

    Google Scholar 

  16. K. Fukunaga, Introduction to Statistical Pattern Recognition. Academic, New York (1972).

    Google Scholar 

Optical Character Recognition(OCR)

  1. G.L. Fischer, Jr., D.K. Pollock, B. Radack and M.E. Stevens (eds), Optical Character Recognition. Spartan Books, Washington, D.C. (1962).

    Google Scholar 

  2. C.N. Liu and G.L. Shelton, JR., “An experimental investigation of a mixed-font print recognition system” IEEE Trans. Computers EC-15 (6), 916–925 (1966).

    Article  Google Scholar 

  3. G. Nagy, “Preliminary investigation of techniques for automated reading of unformatted text,” IBM Res. RC 1867, York-town Heights, New York (30 June 1967)

    Google Scholar 

  4. T. Trickett, “The design of a standard type font for optical character recognition,” Honeywell Comput. Jl. 3 (1), 2–11 (1969).

    Google Scholar 

  5. “Special issue on Optical Character Recognition”, Pattern Recognition 2, No. 3 (September 1970).

    Google Scholar 

  6. J.R. Parks, “A multi-level system of analysis for mixed font and hand-blocked printed character recognition” Automatic Interpretation and Classification of Images, A. Grasselli (ed), pp. 295–322. Academic, New York (1969).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Stanford Electronics Laboratories, 94305, Stanford, California, USA

    Bernard Widrow

Authors
  1. Bernard Widrow
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Electrical Engineering, Purdue University, West Lafayette, Indiana, USA

    K. S. Fu

  2. Center for Information Research, University of Florida, Gainesville, Florida, USA

    Julius T. Tou

Rights and permissions

Reprints and permissions

Copyright information

© 1974 Plenum Press, New York

About this chapter

Cite this chapter

Widrow, B. (1974). The “Rubber-Mask” Technique-II, Pattern Storage and Recognition. In: Fu, K.S., Tou, J.T. (eds) Learning Systems and Intelligent Robots. Springer, Boston, MA. https://doi.org/10.1007/978-1-4684-2106-4_20

Download citation

  • DOI: https://doi.org/10.1007/978-1-4684-2106-4_20

  • Publisher Name: Springer, Boston, MA

  • Print ISBN: 978-1-4684-2108-8

  • Online ISBN: 978-1-4684-2106-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation