**5. Conclusions**

Automatic analysis of images with mosaic-type artifacts and automatic classification of images of interest is sustainable and efficient. The mathematical tools for the analysis of textures are powerful enough if they are combined into feature vectors to obtain classification solutions.

It turns out that the development of logical inference systems using the mosaic ontology is possible and perfectible at the same time, by introducing new variables to refine the decision.

**References**

[1] International Committee for the Conservation on the Mosaic. Available from: https://iccm-mosaics.org/

*DOI: http://dx.doi.org/10.5772/intechopen.92679*

[10] Ioniță S, Ţurcanu-Caruțiu D. Intelligent image processing and optical means for archeological artifacts

*Automation of the Expertise of the Roman Mosaic Arts in Constanta: Analytical and Statistical…*

examination. In: Advanced Methods and New Materials for Cultural Heritage Preservation. London: IntechOpen; 2019

[11] van der Maaten L, Boon P, Lange G, Paijmans H, Postma E. Computer vision and machine learning for archaeology.

Applications and Quantitative Methods in Archaeology. 2006. pp. 476-482. Available from: https://publikationen. uni-tuebingen.de/xmlui/bitstream/ handle/10900/61550/CD49\_Maaten\_

[12] Vertan C, Ciuc M. Fundamental Techniques of Processing and Analysis of Images (in Romanian). Bucharest: Matrix Rom; 2007. pp. 182-184

[13] Matlab product documentation [online]. Available from: https://www. mathworks.com/help/images/ref/reg ionprops.html [Accessed: 15 June 2018]

In: Proceedings of Computer

et\_al\_CAA2006.pdf

[2] Doran J. Systems theory, computer simulations and archaeology. World Archaeology. 1970;**1**(3):289-298

[3] Van Den Dries, Monique Henriëtte. Archaeology and the application of artificial intelligence: Case-studies on use-wear analysis of prehistoric flint tools. 1998. Available from: https:// openaccess.leidenuniv.nl/handle/1887/ 13148 [Accessed: 30 October 2019]

[4] Puyol-Gruart J. Computer science, artificial intelligence and archaeology. BAR International Series. 1999;**757**:19-28

[5] Berni M et al. Smartmuseum: A cultural heritage knowledge exchange platform based on ontology-oriented, context-aware and profiling systems. In: Proceedings of 2009 Electronic Imaging and the Visual Arts EVA'09. 2009

[6] Prabawasari VW et al. Knowledgebased systems in the information system

Transactions on Environment, Energy and Earth Sciences SEEIE. 2016

[7] Poux F et al. 3D point clouds in archaeology: Advances in acquisition, processing and knowledge integration applied to quasi-planar objects. Geosciences. 2017;**7**(4):96

[8] Fernández-López M. Overview of methodologies for building ontologies. In: IJCAI99 Workshop on Ontologies and Problem-Solving Methods: Lessons Learned and Future Trends. Vol. 430.

[9] Corcho O, Fernández-López M, Gómez-Pérez A. Methodologies, tools and languages for building ontologies. Where is their meeting point? Data & Knowledge Engineering. 2003;**46**(1):

1999

41-64

**273**

of Indonesian C. In: DEStech

In this chapter we have integrated into a software application functions for processing the data from the images and calculating some descriptors needed in the classification process. We also presented a solution for using artificial intelligence models consisting of fuzzy inference systems for knowledge in the field of mosaic expertise. Fuzzy systems are estimators for solutions of framing the mosaic portions in the conservation-intervention matrix. The rule bases reflect the human expertise that can then be applied repetitively, thus allowing the automation of decision support within the management of cultural heritage.

The obtained results prove the concept and validate the proposed solution at the experimental level. Like any logical-formal model, validation under relevant conditions is dependent on the correctness of the data. Thus, for a correct analysis, the images of the mosaic, as a primary source of data must meet certain conditions from the acquisition phase, as follows:(i) to be taken at an angle right to the surface of the mosaic (in the direction of normal); (ii) to be captured under uniform lighting conditions, without shadows, reflections, etc.; (iii) to be taken from the same height (constant distance) for the entire surface: and (iv) the resolution must be as high as possible.

Other directions for improving the system response and achieving a ready-touse system for mosaic expertise would be to merge several chromatic variables and descriptors, as well as research to find new morphological descriptors.

#### **Acknowledgements**

This study was supported by the grant PN-III-P1-1.2-PCCDI-2017-0476, no. 51PCCDI/2018, from UEFISCDI-MEN.

### **Author details**

Silviu Ioniță<sup>1</sup> \* and Daniela Ţurcanu-Caruțiu<sup>2</sup>

1 Regional Center of Research and Development for Materials, Processes and Innovative Products Dedicated to The Automotive Industry (CRC&D-Auto), University of Pitești, Pitești, Romania

2 Center of Expertise of Artworks by Advanced Instrumental Methods (CEOAMIA), Ovidius University, Constanța, Romania

\*Address all correspondence to: silviu.ionita@upit.ro

© 2020 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

*Automation of the Expertise of the Roman Mosaic Arts in Constanta: Analytical and Statistical… DOI: http://dx.doi.org/10.5772/intechopen.92679*
