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

Apply

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

Journal Title: Digital Presentation and Preservation of Cultural and Scientific Heritage - Year 2017, Vol 7, Issue

Abstract

Our growing cognisance about the chemo-physical properties of elec-tromagnetic waves and of their interaction with various materials provides ex-panding range of possibilities for quantification and non contact material char-acterization 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 effi-cient 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 ap-plication 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.

Authors and Affiliations

Magdelena Stoyanova, Lilia Pavlova

Keywords

EP ID EP326150
DOI -
Views 143
Downloads 0