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

Bardia Yousefi, Stefano Sfarra, Clemente Ibarra-Castanedo, Nicolas P. Avdelidis, Xavier P.V. Maldague

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)943-955
Number of pages13
JournalJournal of Thermal Analysis and Calorimetry
Volume136
Issue number2
DOIs
Publication statusPublished - 30 Apr 2019

Fingerprint

multisensor fusion
Data fusion
principal components analysis
Factorization
factorization
Principal component analysis
archaeology
arts
Infrared radiation
Defects
evaluation
defects
matrices
factor analysis
Painting
descent
Factor analysis
preprocessing
Nondestructive examination
Computational complexity

Keywords

  • Clustering
  • Gradient-descent-based multiplicative rules
  • Negative matrix factorization analysis
  • Nonnegative least squares (NNLS) active-set algorithm
  • Thermal image segmentation
  • Wavelet data fusion

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Physical and Theoretical Chemistry

Cite this

Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings. / Yousefi, Bardia; Sfarra, Stefano; Ibarra-Castanedo, Clemente; Avdelidis, Nicolas P.; Maldague, Xavier P.V.

In: Journal of Thermal Analysis and Calorimetry, Vol. 136, No. 2, 30.04.2019, p. 943-955.

Research output: Contribution to journalArticle

Yousefi, Bardia ; Sfarra, Stefano ; Ibarra-Castanedo, Clemente ; Avdelidis, Nicolas P. ; Maldague, Xavier P.V. / Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings. In: Journal of Thermal Analysis and Calorimetry. 2019 ; Vol. 136, No. 2. pp. 943-955.
@article{788f274dc5e2485aab4c1177c51351e8,
title = "Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings",
abstract = "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.",
keywords = "Clustering, Gradient-descent-based multiplicative rules, Negative matrix factorization analysis, Nonnegative least squares (NNLS) active-set algorithm, Thermal image segmentation, Wavelet data fusion",
author = "Bardia Yousefi and Stefano Sfarra and Clemente Ibarra-Castanedo and Avdelidis, {Nicolas P.} and Maldague, {Xavier P.V.}",
year = "2019",
month = "4",
day = "30",
doi = "10.1007/s10973-018-7644-6",
language = "English",
volume = "136",
pages = "943--955",
journal = "Journal of Thermal Analysis and Calorimetry",
issn = "1388-6150",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings

AU - Yousefi, Bardia

AU - Sfarra, Stefano

AU - Ibarra-Castanedo, Clemente

AU - Avdelidis, Nicolas P.

AU - Maldague, Xavier P.V.

PY - 2019/4/30

Y1 - 2019/4/30

N2 - 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.

AB - 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.

KW - Clustering

KW - Gradient-descent-based multiplicative rules

KW - Negative matrix factorization analysis

KW - Nonnegative least squares (NNLS) active-set algorithm

KW - Thermal image segmentation

KW - Wavelet data fusion

UR - http://www.scopus.com/inward/record.url?scp=85052945087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052945087&partnerID=8YFLogxK

U2 - 10.1007/s10973-018-7644-6

DO - 10.1007/s10973-018-7644-6

M3 - Article

VL - 136

SP - 943

EP - 955

JO - Journal of Thermal Analysis and Calorimetry

JF - Journal of Thermal Analysis and Calorimetry

SN - 1388-6150

IS - 2

ER -