Features combination for art authentication studies: brushstroke and materials analysis of Amadeo de Souza-Cardoso

This work presents a tool to support authentication studies of paintings attributed to the modernist Portuguese artist Amadeo de Souza-Cardoso (1887-1918). The strategy adopted was to quantify and combine the information extracted from the analysis of the brushstroke with information on the pigments present in the paintings. The brushstroke analysis was performed combining Gabor filter and Scale Invariant Feature Transform. Hyperspectral imaging and elemental analysis were used to compare the materials in the painting with those present in a database of oil paint tubes used by the artist. The outputs of the tool are a quantitative indicator for authenticity, and a mapping image that indicates the areas where materials not coherent with Amadeo’s palette were detected, if any. This output is a simple and effective way of assessing the results of the system. The method was tested in twelve paintings obtaining promising results.

[1]  Rui Jesus.  Recuperação de informação multimédia em memórias pessoais , 2009 .

[2]  T. Poggio,et al.  The Mathematics of Learning: Dealing with Data , 2005, 2005 International Conference on Neural Networks and Brain.

[3]  Ann Dooms,et al.  Report on Digital Image Processing for Art Historians , 2009 .

[4]  Ruth Johnston-Feller,et al.  Color Science in the Examination of Museum Objects: Nondestructive Procedures , 2001 .

[5]  Cristina Montagner,et al.  The brushstroke and materials of Amadeo de Souza-Cardoso combined in an authentication tool , 2015 .

[6]  Eric O. Postma,et al.  Computerized visual analysis of paintings , 2005 .

[7]  Christopher A. Maines,et al.  Color Science in the Examination of Museum Objects , 2002 .

[8]  N. Correia,et al.  Unveiling the hand of a 19th century artist with binary image classification and bag-of-features , 2012, 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP).

[9]  Jia Li,et al.  Image processing for artist identification , 2008, IEEE Signal Processing Magazine.

[10]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Hal Daumé,et al.  A Co-training Approach for Multi-view Spectral Clustering , 2011, ICML.

[12]  José Augusto França.  Amadeo de Souza-Cardoso , 1964 .

[13]  Mauro Barni,et al.  Image processing for the analysis and conservation of paintings: opportunities and challenges , 2005, IEEE Signal Process. Mag..

[14]  Alessandro Piva,et al.  Multispectral imaging of paintings , 2008, IEEE Signal Processing Magazine.

[15]  Eric O. Postma,et al.  Automatic extraction of brushstroke orientation from paintings , 2008, Machine Vision and Applications.

[16]  Jialie Shen,et al.  Stochastic modeling western paintings for effective classification , 2009, Pattern Recognit..

[17]  Browne,et al.  Cross-Validation Methods. , 2000, Journal of mathematical psychology.

[18]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.

[19]  A Doulamis,et al.  Image analysis for artistic style identification , 2012 .

[20]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[21]  Jaap van den Herik,et al.  Digital analysis of Van Gogh’s complementary colours , 2005 .

[22]  Anna Bentkowska-Kafel,et al.  Computer Vision and Image Analysis of Art II , 2010 .

[23]  Nuno Correia,et al.  Analysis of paintings using multi-sensor data , 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

[24]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[25]  N. Keshava,et al.  Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Mathieu Thoury,et al.  Visible and Infrared Imaging Spectroscopy of Picasso's Harlequin Musician: Mapping and Identification of Artist Materials in Situ , 2010, Applied spectroscopy.

[27]  Lucia Toniolo,et al.  A Novel Classification Method for Multispectral Imaging Combined with Portable Raman Spectroscopy for the Analysis of a Painting by Vincent Van Gogh , 2013, Applied spectroscopy.

[28]  Theodore E. Matikas,et al.  Emerging Technologies in Non-Destructive Testing V , 2012 .

[29]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[30]  João Manuel Maciel Linhares,et al.  Correlated color temperature preferred by observers for illumination of artistic paintings. , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[31]  Yonghui Zhao.  Image segmentation and pigment mapping of cultural heritage based on spectral imaging , 2008 .

[32]  Babak Saleh,et al.  Toward automated discovery of artistic influence , 2014, Multimedia Tools and Applications.

[33]  Paola Ricciardi,et al.  Use of imaging spectroscopy, fiber optic reflectance spectroscopy, and X-ray fluorescence to map and identify pigments in illuminated manuscripts , 2014 .

[34]  Prashant Parikh.  A Theory of Communication , 2010 .

[35]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[37]  Stefano Baronti,et al.  Principal component analysis of visible and near-infrared multispectral images of works of art , 1997 .

[38]  David G. Stork.  Computer vision, image analysis, and master art: part 1 , 2006, IEEE MultiMedia.

[39]  David G. Stork,et al.  Computer Vision, Image Analysis, and Master Art: Part 3 , 2007, IEEE MultiMedia.

[40]  E. Hendriks,et al.  Van Gogh ’ s brushstrokes : marks of authenticity ? , 2009 .

[41]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[42]  Nikolaos Doulamis,et al.  Deep supervised learning for hyperspectral data classification through convolutional neural networks , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[43]  Haida Liang,et al.  Advances in multispectral and hyperspectral imaging for archaeology and art conservation , 2012 .

[44]  Richard P. Taylor,et al.  Fractal analysis of Pollock's drip paintings , 1999, Nature.

[45]  S. Nascimento,et al.  The number of discernible colors in natural scenes. , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[46]  Lei Yao,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Rhythmic Brushstrokes Distinguish Van Gogh from His Contemporaries: Findings via Automated Brushstroke Extraction , 2022 .

[47]  Nuno Correia,et al.  Methods for automatic and assisted image annotation , 2011, Multimedia Tools and Applications.

[48]  Alfonso Fernández-Manso,et al.  Spectral unmixing , 2012 .

[49]  Jon Y. Hardeberg,et al.  Pigment Mapping of the Scream (1893) Based on Hyperspectral Imaging , 2014, ICISP.

[50]  Rinaldo Cubeddu,et al.  Insights into Masolino's wall paintings in Castiglione Olona: Advanced reflectance and fluorescence imaging analysis , 2011 .

[51]  Frédéric Jurie,et al.  Sampling Strategies for Bag-of-Features Image Classification , 2006, ECCV.

[52]  David G. Stork,et al.  Computer Vision, Image Analysis, and Master Art: Part 2 , 2006, IEEE MultiMedia.