other hand, using SOM is in itself attractive, because it allows exploiting non-labelled
samples (without expert intervention). However, data projected onto neurons which
are near “natural” class boundaries, are sometimes heterogeneous. If this problem is
overcome, classification could be directly completed by expert neuron labelling [20].
SOM can also constitute an efficient pre-processing phase for a finer classification.
References
1. M. Voiry, F. Houbre, V. Amarger, and V. Madani: Toward Surface Imperfections Diagno-
sis Using Optical Microscopy Imaging in Industrial Environment. ACD Workshop on Ad-
vanced Control and Diagnosis – IAR-ICD 2005, pp. 139-144 (2005)
2. 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, pp. 451-462 (2000)
3. M. Egmont-Petersen, D. de Ridder, and H. Handels: Image Processing with Neural Net-
works - A Review. Pattern Recognition, vol. 35, pp. 2279-2301 (2002)
4. P. Bouchareine: Métrologie des Surfaces. Techniques de l'Ingénieur, vol. R1390 (1999)
5. T. J. Holmes and W. J. Levy: Signal-processing Chracteristics of Differential-Interference-
Contrast Microscopy. Applied Optics, vol. 26, no. 18, pp. 3929-3939 (1987)
6. P. E. J. Flewitt and R. K. Wild: Light Microscopy. in Physical Methods for materials char-
acterisation (1994)
7. A. Choksuriwong, H. Laurent, and B. Emile: Comparison of invariant descriptors for object
recognition. IEEE International Conference on Image Processing (ICIP) pp. 377-380
(2005)
8. S. Derrode, "Représentation de Formes Planes à Niveaux de Gris par Différentes Approxi-
mations de Fourier-Mellin Analytique en vue d'Indexation de Bases d'Images." Phd Thesis
- Université de Rennes I (1999)
9. F. Ghorbel: A Complete Invariant Description for Gray Level Images by the Harmonic
Analysis Approach. Pattern Recognition, vol. 15, pp. 1043-1051 (1994)
10. G. Ravichandran and M. Trivedi: Circular-Mellin features for texture segmentation. IEEE
Trans. Image Processing, vol. 4, pp. 1629-1640 (1995)
11. P. Grassberger and I. Procaccia: Measuring the strangeness of strange attractors. Physica,
vol. D9, pp. 189-208 (1983)
12. F. Camastra and A. Vinciarelli: Intrinsic Dimension Estimation of Data: An Approach
Based on Grassberger-Procaccia's Algorithm. Neural Processing Letters, vol. 14, no. 1, pp.
27-34 (2001)
13. T. Kohonen: Self Organizing Maps, 3rd edition ed. Berlin: Springer (2001)
14. 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, pp. 1358-1384 (1996)
15. J. Heikkonen and J. Lampinen: Building Industrial Applications with Neural Net-
works.,Proc.European Symposium on Intelligent Techniques, ESIT'99 (1999)
16. P. Demartines: Organization Measures and Representations of Kohonen Maps.,First IFIP
Working Group Workshop (1992)
17. P. Demartines and F. Blayo: Kohonen Self-Organizing Maps:Is the Normalization Neces-
sary? Complex Systems, vol. 6, no. 2, pp. 105-123 (1992)
18. Y. Sheng and C. Lejeune: Invariant pattern recognition using Fourier-Mellin transforms
and neural networks. Journal of Optics, vol. 22, no.5, pp. 223-228 (1991)
19. J. Lampinen and E. Oja: Distortion Tolerant Pattern Recognition Based on Self-Organizing
Feature Extraction. IEEE Trans. on Neural Networks, vol. 6, pp. 539-547 (1995)
20. O. Silvén, M. Niskanen, and H. Kauppinen: Wood Inspection with Non-Supervised Clus-
tering. Machine Vision and Applications, vol. 13, no. 5, pp. 275-285 (2000)
34