The CRASH project: Defect detection and classification in ferrite cores

  • Massimo Mari
  • Carlo Dambra
  • Dmitry Chetverikov
  • Judit Verestoy
  • Adam Jozwik
  • Mariusz Nieniewski
  • Leszek Chmielewski
  • Marek Sklodowski
  • Waldemar Cudny
  • Martin Lugg
Special Session on European Projects
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)

Abstract

The paper presents a work developed in the framework of the two years COPERNICUS technological research project CRASH (CRack and SHape defect detection in ferrite cores) CIPA-CT94 0I53, in progress since 1995.

The CRASH project concerns automated quality inspection of ferrite cores. CRASH studies the development of optical and electromagnetic systems that may be integrated in a working module to increase the recognition of imperfections on ferrite materials. Analysis and processing of acquired images and signals, as well as specification of ad-hoc algorithms for classification purposes constitute the technical approach to the problem. The achieved results show the capability of the system to detect different kind of imperfections in ferrite cores (shape defects, surface defects and subsurface imperfections) and classify them with low error rates.

After an introduction to the problem in Section 1, different techniques of defect detection with different sensors are shown in Section 2, and Section 3 describes the achieved classification results.

References

  1. 1.
    The CRASH project official home page is at http://www.Iii.unitn.it The CRASH Consortium: UNT University of Trento, Rovereto ITALY-Project Coordinator HAS Hungarian Academy of Sciences, Budapest HUNGARY PAS Polish Academy of Sciences, Warsaw POLAND AIP Association of Image Processing, Warsaw POLAND TSC Technical Software Consultant Ltd., Milton Keynes UK POLFER POLFER Magnetic Materials, Warsaw POLAND.Google Scholar
  2. 2.
    D. Mirshekar-Syahkal, R. Collins and D. H. Michael, “Developments in surface cracks by the A.C. field technique”, Review of progress in quantitative NDT Evaluation, Donald O. Thompson et al. eds., Plenum Publishing, 1985, pp. 349–357.Google Scholar
  3. 3.
    M. Nieniewski, Morphological Method of Detection of defects on the Surface of Ferrite Cores, Proc. 10th Scandinavian Conference on Image Analysis, Lappeenranta, Jun 1997.Google Scholar
  4. 4.
    K. I. Laws, Textured image segmentation, Univ. of Southern California, Image Processing Institute, USCIPI Report 940, Jan 1980.Google Scholar
  5. 5.
    W. K. Pratt, Digital Image Processing, John Wiley, New York 1991.Google Scholar
  6. 6.
    C-M. Wu, Y-C. Chen, Statistical feature matrix for texture analysis, CVGIP: Graphical Models and Image Processing, 54, 5, 1992, pp. 407–419.CrossRefGoogle Scholar
  7. 7.
    A.Jozwik, L.Chmielewski, W.Cudny, M.Sklodowski, A 1-NN preclassifier for fuzzy k-NN rule, Proc. 13th Int. Conf. Pattern Recognition, ICPR96, Wien, Austria, August 1996, Track D, pp. 234–238.Google Scholar
  8. 8.
    Z. Wu, “Homogeneity testing for unlabeled data: a performance evaluation”, Graphical Models and Image Processing, vol.55, September 1993, pp.370–380.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 1997

Authors and Affiliations

  • Massimo Mari
    • 1
  • Carlo Dambra
    • 1
  • Dmitry Chetverikov
    • 1
  • Judit Verestoy
    • 2
  • Adam Jozwik
    • 3
  • Mariusz Nieniewski
    • 4
  • Leszek Chmielewski
    • 5
  • Marek Sklodowski
    • 5
  • Waldemar Cudny
    • 5
  • Martin Lugg
    • 6
  1. 1.University of Trento, Laboratorio di Ingegneria InformaticaRoveretoItaly
  2. 2.Hungarian Academy of ScienceComputer and Automation Research InstituteBudapestHungary
  3. 3.Polish Academy of SciencesInstitute of Biocybernetics and Biomedical EngineeringWarsawPoland
  4. 4.Department of Fundamental Research in Electrical Eng.Polish Academy of SciencesWarsawPoland
  5. 5.Association for Image Processing, IFTR PASWarsawPoland
  6. 6.Technical Software Consultant Ltd., 6 Mill SquareWolwerton MillUK

Personalised recommendations