Polak, A. and Kelman, T. and Murray, P. and Marshall, S. and Stothard, D.J.M. and Eastaugh, N. and Eastaugh, F. (2016) Use of hyperspectral imaging for artwork authentication. In: International Association for Spectral Imaging, 2016-07-03 - 2016-07-06.
Polak_IASIM_2017_Use_of_hyperspectral_imaging_for_artwork_authentication.pdf - Final Published Version
Download (309kB) | Preview
In recent years various scientific practices have been adapted to the artwork analysis process and a set of techniques was found advantageous for conservation and restoration works. Apart of these applications, art market also benefits from scientific testing of artwork. Although these services are available to determine authenticity of traded pieces, they are very expensive and time consuming and therefore serve only very limited range of transactions. As a response for requirements of growing market there is a need for rapid and non-destructive methods empowering art authentication. Hyperspectral imaging combined with signal processing and classification techniques are proposed as a tool to enhance the identification of art forgeries. Using bespoke paintings designed for this work, a spectral library of selected pigments was established and the viability of training and the application of classification techniques based on this data was demonstrated. Developed techniques were used for the analysis of actual forged paintings held by the Berlin police, which comprised known and suspected forgeries from the infamous Beltracchi case. The analysis resulted in the identification of anachronistic paint, confirming the falsity of the artwork. Figure 1 illustrates one of analysed paintings and result of the classification, indicating Titanium White – a pigment known as anachronistic for this case.
|Item type:||Conference or Workshop Item (Other)|
|Keywords:||hyperspectral imaging (HSI), infrared, artwork authentication, support vector machine (SVM), Electrical engineering. Electronics Nuclear engineering, Electrical and Electronic Engineering, Signal Processing|
|Subjects:||Technology > Electrical engineering. Electronics Nuclear engineering|
|Department:||Faculty of Engineering > Electronic and Electrical Engineering
Technology and Innovation Centre > Sensors and Asset Management
|Depositing user:||Pure Administrator|
|Date Deposited:||08 Mar 2017 13:56|
|Last modified:||08 Mar 2017 14:22|