Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings

• Published in: Journal of thermal analysis and calorimetry Vol. 136; no. 2; pp. 943 - 955
• Main Authors: Yousefi, Bardia, Sfarra, Stefano, Ibarra-Castanedo, Clemente, Avdelidis, Nicolas P., Maldague, Xavier P. V.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.04.2019; Springer; Springer Nature B.V
• Subjects: Algorithms; Analytical Chemistry; Archaeology; Arts; Chemistry; Chemistry and Materials Science; Clustering; Covariance; Cultural heritage; Cultural resources; Data integration; Defects; Factor analysis; Factorization; Historical buildings; Inorganic Chemistry; Measurement Science and Instrumentation; Medical research; Multisensor fusion; Nondestructive testing; Painting (Art); Physical Chemistry; Polymer Sciences; Principal components analysis; Segmentation; Technology; Thermography; Wavelet analysis; Negative matrix factorization analysis; Wavelet data fusion; Thermal image segmentation; Clustering; Gradient-descent-based multiplicative rules; Nonnegative least squares (NNLS) active-set algorithm
• ISSN: 1388-6150; 1588-2926
• DOI: 10.1007/s10973-018-7644-6

The application of the thermal and infrared technology in different areas of research is considerably increasing. These applications involve nondestructive testing, medical analysis (computer aid diagnosis/detection—CAD), and arts and archeology, among many others. In the arts and archeology field, infrared technology provides significant contributions in terms of finding defects of possible impaired regions. This has been done through a wide range of different thermographic experiments and infrared methods. The proposed approach here focuses on application of some known factor analysis methods such as standard nonnegative matrix factorization (NMF) optimized by gradient-descent-based multiplicative rules (SNMF1) and standard NMF optimized by nonnegative least squares active-set algorithm (SNMF2) and eigen-decomposition approaches such as principal component analysis (PCA) in thermography, and candid covariance-free incremental principal component analysis in thermography to obtain the thermal features. On the one hand, these methods are usually applied as preprocessing before clustering for the purpose of segmentation of possible defects. On the other hand, a wavelet-based data fusion combines the data of each method with PCA to increase the accuracy of the algorithm. The quantitative assessment of these approaches indicates considerable segmentation along with the reasonable computational complexity. It shows the promising performance and demonstrated a confirmation for the outlined properties. In particular, a polychromatic wooden statue, a fresco, a painting on canvas, and a building were analyzed using the above-mentioned methods, and the accuracy of defect (or targeted) region segmentation up to 71.98%, 57.10%, 49.27%, and 68.53% was obtained, respectively.