The IFIDA Project: Intelligent Fast Interconnected Devices and Tools for Applications in Archaeometry and Conservation Practice

2017

DiPP

Self Cite

Our growing cognisance about the chemo-physical properties of electromagnetic waves and of their interaction with various materials provides expanding range of possibilities for quantification and non contact material characterization even in difficult to computation, « non-standard » domains as this of the cultural heritage. This review - thematically part of the IFIDA project dedicated to digitization of archaeometric and conservation-restoration praxis - deals with the possibilities latest neuroinformatic methods offer for a more efficient and fast interrogation, understanding and classification of multi-modal spectral records of paintings on various supports. The workflow followed during their routine non destructive (ND) analysis by human experts is described in terms of specific technical characteristics, research objectives and concrete application for the artworks' characterization as a prototype to simulate artificially. References to techniques for high semantic level information extraction from low-level features are suggested. The strengths and limitations in application of Deep Belief Networks (DBNs) for compression, visualization and data recognition are also considered. Examples of most appropriate architectures and topological maps of Deep Learning Networks for interpretation of UV, IR, XR, β, γ and CT records performing simple characterization and classification tasks - from single layer perceptron to multi-layer deep belief neural networks for unlabelled data - are presented and explained.

Section: Actually Existing Methods For Image Classification and Inter...mentioning

confidence: 99%

Deep Belief Networks for Multimodal, Images-based Non Contact Material Characterization

2017

DiPP

Self Cite

“…This paper illustrates the application of an appositely elaborated ontology-based knowledge model (Stoyanova, 2014) (Stoyanova, 2015) (Stoyanova & Lukić, 2015) (Stoyanova & Pavlova, 2017), (Stoyanova, Stoyanov & Pavlova, 2018) dedicated to digitization of Byzantine and post Byzantine painting and functional to archaeometric and conservation purposes. It is intended to assist authentication, attribution and dating, reasoning through defined semantic data collected from digital multimodal & multidimensional images which describe the physical and chemical characteristics of the studied objects.…”

Section: Introductionmentioning

confidence: 99%

Digital Imaging Techniques in Archaeometry: The Case of an Ancient Crucifixion Icon

Stoyanov

2022

DiPP

Self Cite

An ancient Crucifixion icon has been studied using imaging techniques integrated with appropriated visualizations. Relevant parameters and suitable algorithms have been selected in a proper sequence to segment the studied images into meaningful elements functional to the attribution of the icon through analysis of the employed materials and techniques. The cross-referencing of the results allowed to identify three main phases in the realization of the painting, to describe their extension, character and determine the possible authors as: Cretan/Ionian painters, '500-' 600 (1 st phase); Hristofor Žefarović, Western Balkans or Vienna, 1730-1753 (2 nd phase); Placido Fabris / Michelangelo Barbini, Venice, mid 19 th c. (3 rd phase).

“…As in reality it is impossible to isolate them, the first being constructive elements of the second, in this paper we advance a general model of their interrelations that will be used for the elaboration of tools in support of attribution, conservation and restoration of easel/icon painting [1]. The implementation of these objectives is partially funded by COST TD121 COSCH and will benefit from the technological section of the BIDL project [2][12] [13], at the same time contributing to its further development as well as to the realization of the wider IFIDA programme, presented at the DiPP2014 conference [3].…”

Section: Introductionmentioning

confidence: 99%

Technical Visualizations of Easel Painting. Integration of Imaging Techniques and Textual Repertories

Проворова

et al. 2015

DiPP

Self Cite

Technical visualizations (TV) of easel painting, both partial or extended, are typically concerned with prospecting its structure, technique, material composition and eventual posterior interventions in order to facilitate the mapping of its characteristics being identical to those of other similar objects. For both types the main challenge is being able to integrate and compare the significant increase in the quantity and quality of image-based data resulting from rapid technological advancement in recent years. Their second critical component matches the algorithm of logical processes that, in principle, should be followed by analysis of a specific artistic technique on a unique artefact. The third crucial point is the translation of interdisciplinary to schematic or imagebased data and the standardization of dictionaries used to enable their sharing. TVs are functional to the understanding of complex cases and, although the reliability of their issues is not absolute but only a nulla osta, they represent an important step towards the drastic reduction of errors produced by discontinued, fragmentary experiments in dating and authentication of easel painting.