Abstract
This paper deals with the classification of defects in web type products. Detection of outliers in the training set and objective determination of the defect classes represent an important step towards standardization of the defect classes. An approach that is based on the Generalized Principal Co-ordinate Analysis (GPCA) is described for objective selection of a training set and adaptive class cleaning in a low dimensionality space. This approach is applied on features extracted by modelling the production process by an ergodic process which is characterized by its Autocorrelation Function (ACF). An important advantage of this method is its suitability for large pattern vectors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alam Eldin, A.T. and Nour Eldin, H.A., “Automated visual inspection of uniformly textured flat surfaces using correlation analysis” Proceedings of the IASTED International Symposium:Applied Control, Filtering, and Signal Processing”, June 15–17,1987, Geneva, Switzerland.
Chatfield, C. and Collins, A., “Introduction to Multivariate Analysis”, Chapman and Hall 1980.
Goldfarb, L., “A Unified Approach to Pattern Recognition”, Pattern Recognition, Vol. 17, No. 5, pp.575–582, 1984.
Goldfarb, L., “A New Approach to Pattern Recognition”, in Progress in Pattern Recognition, vol. 2. ed. L. Kanal and A. Rosenfeld, Elsevier Science Publishers B.V. 1985.
Goldfarb, L., “Metric Data Models And Associative Memories”, invited paper presented at the 8th IASTED International Symposium on Robotics and Artificial intelligenece, June 18–20, 1986, Toulouse (France).
Goodfrey, K.R., “Correlation Methods”, Automatica, Vol 16., pp 527–534.
A. D. Gordon,”Classification- Methods for the Exploratory Analysis of Multivariate Data”, Chapman and Hall, 1981.
Gower, J.C., “Some distance properties of latent root and vector methods used in multivariate analysis”. Biometrika, 53, pp. 325–338.
Jolliffe, I.T.,”Principal Component Analysis”, Springer Verlag, 1986
Kruskal, J.B., “Nonmetric Multidimensional Scaling: A numerical method” Psychometrika-Vol.29, No. 2, June 1964.
Torgerson, W.S.,”Multidimensional scaling: I. Theory and method”.Psycho-metrika, 17, pp.401–419, 1966.
Yaglom, A.M., “Correlation theory of stationary and related random functions I: basic results”, Springer-Verlag, 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eldin, A.T.A., Eldin, H.A.N. (1988). Automated Inspection of Web Type Products in Pseudo-euclidean Spaces. In: Bunke, H., Kübler, O., Stucki, P. (eds) Mustererkennung 1988. Informatik-Fachberichte, vol 180. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-08895-1_36
Download citation
DOI: https://doi.org/10.1007/978-3-662-08895-1_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-50280-7
Online ISBN: 978-3-662-08895-1
eBook Packages: Springer Book Archive