A Curvature Primal Sketch Neural Network Recognition System

  • Michael Fairbank
  • Andrew Tuson
Conference paper


Neural networks can be used to classify images such as handwritten characters. A common method of doing this involves mapping the pixel values of the image onto the input nodes of a feed-forward net. This is problematic in that the topological properties of the original image space, such as the spatial relations between different pixels, are not immediately apparent to the net. We address this problem by using the real valued coordinates of selected features in the image for input to the net.

This paper details a formative study of the Curvature Primal Sketch (CPS) as a preprocessing method to identify the interesting features of the curves that make up handwritten characters. Emphasis is placed upon integrating the CPS with a feedforward neural network classifier. To this end, we describe an algorithm for selecting which of the features produced by the CPS should be used as input to the neural network. We postulate that the order in which the features are used as inputs to the net is also important and introduce a solution to this problem.

The nets obtained by this approach were small and performed recognition well. A net with dimensions 14–14–10 was trained with collection of 500 handwritten digits, collected from different people. On a similar test set of 100 digits, the net was found to achieve 92.8% accuracy in recognition.


Neural Network Classifier Handwritten Digit Handwritten Character Curvature Primal Scale Space Representation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Asada, H. and Brady, M.: The Curvature Primal Sketch. AI Lab Memo 758, Massachusetts Institute of Technology, 1984.Google Scholar
  2. [2]
    Fairbank, M.: A Neural Network Vision System based on the Curvature Primal Sketch. MSc thesis, Department of Artificial Intelligence, University of Edinburgh, 1995.Google Scholar
  3. [3]
    Le Cun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D.: Handwritten digit recognition with a back-propagation network. In Advances in Neural Information Processing Systems, volume 2. San Mateo: Morgan Kaufmann, 1990.Google Scholar
  4. [4]
    Denker, J. S., Gardner, W. R., and Graf, H. P.: Neural network recogniser for handwritten zip-code digits. In Advances in Neural Information Processing Systems, volume 1, AT&T Bell Labs, 1988.Google Scholar
  5. [5]
    Martin, G. L. and Pittman, J. A.: Recognising handprinted letters and digits. In Advances in Neural Information Processing Systems, volume 2. San Mateo: Morgan Kaufmann, 1990.Google Scholar
  6. [6]
    Tveter, D. R.: The ‘rbp’ back-propagation simulation program. 5228 N. Nashville Ave, Chicago, Illinois 60656.Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • Michael Fairbank
    • 1
  • Andrew Tuson
    • 2
  1. 1.Division of InformaticsEdinburgh UniversityEdinburghUK
  2. 2.Department of ComputingCity UniversityLondonUK

Personalised recommendations