Cultural Heritage Applications: Archaeological Ceramics and Building Restoration - On Statistical Pattern Recognition in Independent Component Analysis Mixture Modelling - page 150

The second application was the restoration of historical buildings where the
one-ICA version of Mixca was applied. The ICA model for ultrasound evaluation
as the superposition of the backscattered signal plus sinusoidal phenomena was
tested by means of two novel applications: consolidation diagnosis and layer
determination in heritage building restoration. The application of ICA to NDT by
ultrasounds has enabled the diagnosis of the consolidation status in the restoration
of historical buildings. The proposed procedure allowed the sources corresponding
to the contributions of consolidated and non-consolidated zones in the backscat-
tered recorded signals to be separated.
The application of ICA to NDT by ultrasounds made the determination of the
thickness of the material profile possible and allowed interferences from the
recorded signals to be cancelled. The enhanced B-Scan enabled the thickness of
the first layer of mortar to be determined. ICA works well in the case of a rela-
tively high interference level with respect to the ultrasonic signal.
Enhanced power and centroid frequency B-Scans were obtained using ICA as
preprocessor of the non-stationary analysis. Future work is being addressed to
apply the ICA for classification and characterization of materials.

References

1. A. Salazar, L. Vergara, ICA mixtures applied to ultrasonic non-destructive classification of
archaeological ceramics. EURASIP J. Adv. Signal Process. vol. 2010, Article ID 125201, 11
pages, doi: 10.1155/2010/125201 (2010)
2. R.E. Taylor, M.J. Aitken, Chronometric Dating in Archaeology, Advances in archaeological
and museum science series, vol 2 (Springer-Verlag, New York USA, 1997)
3. R. Cribbs, F. Saleh, An ultrasonic based system used for non-destructive imaging of
archaeological sites, in Proceedings of Informatica ed Egittologia all'inizio degli anni'90,
(Roma Italy, 1996), pp. 97-108
4. A. Murray, M.F. Mecklenburg, C.M. Fortenko, R.E. Green, Detection of delaminations in art
objects using air-coupled ultrasound, in Proceedings of Materials Issues in Art and

Archaeology III, (San Francisco USA, 1992), pp. 371-378
5. W.I. Sellers, Ultrasonic cave mapping. J. Archaeological Science 25(9), 867-873 (1998)
6. A. Salazar, R. Miralles, A. Parra, L. Vergara, J. Gosalbez, Ultrasonic signal processing for
archaeological ceramic restoration, in Proceedings of 31st IEEE International Conference on
Acoustics, Speech, and Signal Processing, ICASSP, (Toulouse, France, 2006), pp. III-
1160-1163
7. L. Cohen, P. Loughlin, Recent Developments in Time-Frequency Analysis (Springer-Verlag,
New York USA, 1998)
8. R. Miralles, L. Vergara, A. Salazar, J. Igual, Blind detection of nonlinearities in ultrasonic
grain noise. IEEE Trans. Ultrasonics, Ferroelectrics, and Frequency Control 55(3), 637-647
(2008)
9. A.K. Jain, Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis
and Machine Intelligence 22(1), 4-37 (2000)
10. O. Chapelle, B. Schölkopf, A. Zien, Semi-supervised Learning, MIT Press, 2006.
11. A. Salazar, L. Vergara, A. Serrano, J. Igual, A general procedure for learning mixtures of
independent component analyzers. Pattern Recognition 43(1), 69-85 (2010)