Impact of Data Dimensionality Reduction on Neural Based Classification: Application to Industrial Defects

Matthieu Voiry, Kurosh Madani, Véronique Amarger, Joël Bernier

2007

Abstract

A major step for high-quality optical surfaces faults diagnosis concerns scratches and digs defects characterisation. This challenging operation is very important since it is directly linked with the produced optical component’s quality. To complete optical devices diagnosis, a classification phase is mandatory since a number of correctable defects are usually present beside the potential “abiding” ones. Unfortunately relevant data extracted from raw image during defects detection phase are high dimensional. This can have harmful effect on behaviors of artificial neural networks which are suitable to perform such a challenging classification. Reducing data dimension to a smaller value can however decrease problems related to high dimensionality. In this paper we compare different techniques which permit dimensionality reduction and evaluate their possible impact on classification tasks performances.

References

  1. M. Voiry, F. Houbre, V. Amarger, and K. Madani: Toward Surface Imperfections Diagnosis Using Optical Microscopy Imaging in Industrial Environment.IAR & ACD, p.139-144 (2005).
  2. M. Voiry, V. Amarger, K. Madani, and F. Houbre: Combining Image Processing and Self Organizing Artificial Neural Network Based Approaches for Industrial Process Faults Clustering . 13th International Multi-Conference on Advanced Computer Systems, p.129-138 (2006).
  3. M. Voiry, K. Madani, V. Amarger, and F. Houbre: Toward Automatic Defects Clustering in Industrial Production Process Combining Optical Detection and Unsupervised Artificial Neural Network Techniques. Procedings of the 2nd International Workshop on Artificial Neural Networks and Intelligent Information Processing - ANNIIP 2006, p.25-34 (2006).
  4. G. P. Zhang: Neural Networks for Classification: A Survey, IEEE Trans. on Systems, Man, and Cybernetics - Part C: Applications and Reviews, vol. 30, no. 4, p.451-462 (2000).
  5. M. Egmont-Petersen, D. de Ridder, and H. Handels : Image Processing with Neural Networks - A Review, Pattern Recognition, vol. 35, p.2279-2301 (2002).
  6. K. Boehm, W. Broll, and M. Sokolewicz: Dynamic Gesture Recognition Using Neural Networks; A Fundament for Advanced Interaction Construction, Proceedings of SPIE, vol. 2177, Stereoscopic Displays and Virtual Reality Systems (1994).
  7. J. Lampinen and E. Oja: Distortion Tolerant Pattern Recognition Based on Self-Organizing Feature Extraction, IEEE Trans. on Neural Networks vol. 6, p.539-547(1995).
  8. S. Buchala, N. Davey, T. M. Gale, and R. J. Frank: Analysis of Linear and Nonlinear Dimensionality Reduction Methods for Gender Classifcation of Face Images, International Journal of Systems Science (2005).
  9. M. Verleysen: Learning high-dimensional data. LFTNC'2001 - NATO Advanced Research Workshop on Limitations and Future Trends in Neural Computing (2001).
  10. M. Lennon, G. Mercier, M. C. Mouchot, and L. Hubert-Moy: Curvilinear Component Analysis for Nonlinear Dimensionality Reduction of Hyperspectral Images, Proceedings of SPIE, vol. 4541, Image and Signal Processing for Remote Sensing VII, p.157-168 (2001).
  11. P. Demartines, "Analyse de Données par Réseaux de Neurones Auto-Organisés." PhD Thesis, Institut National Polytechnique de Grenoble (1994).
  12. T. Kohonen: Self Organizing Maps, 3rd edition ed. Berlin: Springer (2001).
  13. T. Kohonen, E. Oja, O. Simula, A. Visa, and J. Kangas: Engineering Applications of the Self-Organizing Maps, Proceedings of the IEEE, vol. 84, no. 10, p.1358-1384 (1996).
  14. J. Heikkonen and J. Lampinen: Building Industrial Applications with Neural Networks.,Proc.European Symposium on Intelligent Techniques, ESIT'99 (1999).
  15. P. Demartines and J. Hérault: Vector Quantization and Projection Neural Network, Lecture Notes in Computer Science, vol. 686, International Workshop on Artificial Neural Networks, p.328-333 (1993).
  16. P. Demartines and J. Hérault: CCA : "Curvilinear Component Analysis", Proceedings of 15th workshop GRETSI (1995).
  17. J. A. Lee, A. Lendasse, N. Donckers, and M. Verleysen: A Robust Nonlinear Projection Method, European Symposium on Artificial Neural Networks - ESANN'2000 (2000).
  18. S. Derrode, "Représentation de Formes Planes à Niveaux de Gris par Différentes Approximations de Fourier-Mellin Analytique en vue d'Indexation de Bases d'Images." PhD Thesis , Université de Rennes I (1999).
  19. F. Ghorbel: A Complete Invariant Description for Gray Level Images by the Harmonic Analysis Approach, Pattern Recognition, vol. 15, p.1043-1051 (1994).
  20. P. Demartines and F. Blayo: Kohonen Self-Organizing Maps:Is the Normalization Necessary?, Complex Systems, vol. 6, no. 2, p.105-123 (1992).
  21. J. E. Dennis and R. B. Schnabel: Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Englewood Cliffs, NJ: Prentice Hall (1983).
Download


Paper Citation


in Harvard Style

Voiry M., Madani K., Amarger V. and Bernier J. (2007). Impact of Data Dimensionality Reduction on Neural Based Classification: Application to Industrial Defects . In Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007) ISBN 978-972-8865-86-3, pages 56-65. DOI: 10.5220/0001635500560065


in Bibtex Style

@conference{anniip07,
author={Matthieu Voiry and Kurosh Madani and Véronique Amarger and Joël Bernier},
title={Impact of Data Dimensionality Reduction on Neural Based Classification: Application to Industrial Defects},
booktitle={Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007)},
year={2007},
pages={56-65},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001635500560065},
isbn={978-972-8865-86-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2007)
TI - Impact of Data Dimensionality Reduction on Neural Based Classification: Application to Industrial Defects
SN - 978-972-8865-86-3
AU - Voiry M.
AU - Madani K.
AU - Amarger V.
AU - Bernier J.
PY - 2007
SP - 56
EP - 65
DO - 10.5220/0001635500560065