Advertisement

Multimedia Tools and Applications

, Volume 75, Issue 7, pp 4039–4063 | Cite as

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

  • Cristina MontagnerEmail author
  • Rui Jesus
  • Nuno Correia
  • Márcia Vilarigues
  • Rita Macedo
  • Maria João Melo
Article

Abstract

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.

Keywords

Painting analysis Gabor SIFT Hyperspectral imaging Authentication 

Notes

Acknowledgments

This work has been supported by national funds through FCT- Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) under project PTDC/EAT-EAT/113612/2009 and grant of Cristina Montagner SFRH/BD/66488/2009 as well as REQUIMTE supporting project PEst-C/EQB/LA0006/2011. The authors are grateful to all team members of CAM - Centro de Arte Moderna da Fundação Gulbenkian for the fruitful collaboration, in particular to director Isabel Carlos and curator Ana Vasconcelos e Melo. Thanks also to Professor Sérgio Nascimento, João M.M. Linhares, Osamu Masuda and Hélder Tiago Correia for the spectral imaging analysis.

References

  1. 1.
    Al-Ayyoub M, Irfan MT, Stork DG (2011) Computer vision and Image Analysis of Art II. 7869Google Scholar
  2. 2.
    Alfaro C (2008) Critérios e metodologia, in Catálogo Raisonné V.2 – Amadeo de Souza-Cardoso, pintura, A.A.a.F.C. Gulbenkian, Editor. LisbonGoogle Scholar
  3. 3.
    Almeida P (2012) Análise e Identificação de Obras de Arte. Universidade NOVA de Lisboa, Faculdade De Ciências e Tecnologia, Portugal LisbonGoogle Scholar
  4. 4.
    Almeida P et al (2013) Analysis of paintings using multi-sensor data, in Signal Processing Conference (EUSIPCO), IEEE, Editor. Marrakech. p. 1-5Google Scholar
  5. 5.
    Barni M, Pelagotti A, Piva A (2005) Image processing for the analysis and conservation of paintings: opportunities and challenges. Signal Proc Mag IEEE 22(5):141–144CrossRefGoogle Scholar
  6. 6.
    Baronti S et al (1997) Principal Component Analysis of visible and near-infrared multispectral images of work of art. Chemom Intell Lab Syst 39(1):103–144CrossRefGoogle Scholar
  7. 7.
    Berezhnoy IE, Postma EO, Herik van den HJ (2005) Computerized visual analysis of paintings. in Humanities, computers and cultural heritage: Proceedings of the XVI international conference of the Association for History and Computing. Amsterdam: Amsterdam: Royal Netherlands Academy of Arts and SciencesGoogle Scholar
  8. 8.
    Berezhnoy IE et al (2009) Automatic extraction of brushstroke orientation from paintings. POET: Prevailing Orientation Extraction Technique. Mach Vis Appl 20:1–9CrossRefGoogle Scholar
  9. 9.
    Boselli L, Picollo M, Radicati B (2011) UV Vis, NIR Fibre Optic Reflectance Spectroscopy (FORS) in Practical handbook on diagnosis of paintings on movable support, R.M. D. Pinna, B. Brunetti, Editor, ArtechGoogle Scholar
  10. 10.
    Browne MW (2000) Cross-Validation Methods. J Math Psychol 44(1):108–132MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Cesaratto A et al (2013) A novel classification method for multispectral imaging combined with portable Raman spectroscopy for the analysis of a painting by Vincent van Gogh. Appl Spectroscopy 67(11):1234–41CrossRefGoogle Scholar
  12. 12.
    Comelli D et al (2011) Insights into Masolino’s wall paintings in Castiglione Olona: advanced reflectance and fluorescence imaging analysis. J Cultural Heritage 12(1):11–18CrossRefGoogle Scholar
  13. 13.
    Cornelis B et al (2009) Report on Digital Image Processing for Art Historians, in International Conference on Sampling Theory and Applications. Marseille, FranceGoogle Scholar
  14. 14.
    Deborah H, George S, Hardeberg JY (2014) Pigment mapping of the Scream (1893) based on hyperspectral imaging. in ICIP. Cherbourg, France Springer International Publishing.Google Scholar
  15. 15.
    Delaney JK et al (2010) Visible and infrared imaging spectroscopy of Picasso’s Harlequin musician: mapping and identification of artist materials in situ. Appl Spectrosc 64(6):584–594CrossRefGoogle Scholar
  16. 16.
    Delaney JK et al (2014) Use of imaging spectroscopy, Fiber Optic Reflectance Spectroscopy, and X-ray fluorescence to map and identify pigments in illuminated manuscripts. Studies In Conservation 59(2):91–101CrossRefGoogle Scholar
  17. 17.
    Doulamis AD, Varvarigou TA (2011) Image analysis for artistic style identification: A powerful tool for preserving Cultural Heritage. in 5th Conference on Emerging Technologies in Non-Destructive Testing VGoogle Scholar
  18. 18.
    Erhan D et al (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11:625–660MathSciNetzbMATHGoogle Scholar
  19. 19.
    Feller RJ (2004) Color science in the examination of museum objects: non-destructive procedures. The Getty Conservation Institute, Los AngelesGoogle Scholar
  20. 20.
    França JA, Amadeo de Souza-Cardoso (1956) Lisbona:Sul.LisbonGoogle Scholar
  21. 21.
    Freitas H, Alfaro C (2008) Catálogo Raisonné V.2 – Amadeo de Souza-Cardoso, pintura, ed. A.A.a.F.C. Gulbenkian, LisbonGoogle Scholar
  22. 22.
    Freitas H, Alfaro C, Rosa M (2006) Diálogo de Vanguardas-Avant-Garde Dialogues. Lisbon: Assírio & Alvim and Fundação Calouste Gulbenkian.Google Scholar
  23. 23.
    Gabor D (1946) Theory of communication. J Ins Electric Eng Part III: Radio Commun Eng 93(26):429–441Google Scholar
  24. 24.
    Hendriks E, Hughes S (2009) van Gogh’s brushstrokes: marks of authenticity? in Art, conservation and authenticities: material, concept, context international conference, Archetype, Editor. London. p. 143-154Google Scholar
  25. 25.
    Hendriks E, Tilborgh van L (2006) New views on Van Gogh’s development in Antwerp and Paris: An integrated art historical and technical study of his paintings in the Van Gogh Museum, in Faculty of Humanities. Univ. AmsterdamGoogle Scholar
  26. 26.
    Jesus R (2009) Recuperação de informação multimédia em memórias pessoais, in Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia, Portugal, Lisbon.Google Scholar
  27. 27.
    Jesus R, Abrantes A, Correia N (2010) Methods for automatic and assisted image annotation. Multimedia Tools and Applications, p. 1-20Google Scholar
  28. 28.
    Johnson CR et al (2008) Image processing for artist identification computerized analysis of Vincent van Gogh’s painting brushstrokes. IEEE Signal Process Mag 25(4):37–48CrossRefGoogle Scholar
  29. 29.
    Keshava N (2004) Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries. IEEE Trans Geosci Remote Sens 42(7):1552–1565CrossRefGoogle Scholar
  30. 30.
    Keshava N, Mustard JF (2002) Spectral Unmixing. IEEE Signal Process Mag 19(1):44–57CrossRefGoogle Scholar
  31. 31.
    Kumar A, Daumé H III (2011) A Co-training approach for multi-view spectral clustering. in Proceedings of the 28th International Conference on Machine Learning (ICML 2011). Bellevue, Washington, USA.Google Scholar
  32. 32.
    Lew MS et al (2006) Content-based multimedia information retrieval: state of the art and challenges. ACM Trans Multimed Comput Commun Appl 2(1):1–19MathSciNetCrossRefGoogle Scholar
  33. 33.
    Li J et al (2012) Rhythmic brushstrokes distinguish van Gogh from his contemporaries: findings via automated brushstroke extraction Pattern Analysis and Machine Intelligence. IEEE Trans 34(6):1159–1176Google Scholar
  34. 34.
    Liang H (2012) Advances in multispectral and hyperspectral imaging for archaeology and art conservation. Applied Physic A 106:309–323CrossRefGoogle Scholar
  35. 35.
    Linhares JMM, Pinto PD, Nascimento SMC (2008) The number of discernible colors in natural scenes. J Optic Soc Am Optics Image Scie Vision 25(12):2918–2924CrossRefGoogle Scholar
  36. 36.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, p. 91-110Google Scholar
  37. 37.
    Lowe DG (1999) Object recognition from local scale-invariant features, in International Conference on Computer Vision. Corfu, Greece. p. 1150-1157Google Scholar
  38. 38.
    Maarten van der L, Postma E (2008) Digital analysis of van Gogh paintings, in AAAI Conference on Artificial intelligenceGoogle Scholar
  39. 39.
    Makantasis K et al (2015) Deep supervised learning for hyperspectral data classification through convolutional neural networks, in Geoscience and Remote Sensing Symposium (IGARSS 2015).Google Scholar
  40. 40.
    Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8): p. 837-842Google Scholar
  41. 41.
    Melo MJ et al (2008) Uma mão cheia de cores, O Século XX e o nascimento da arte moderna, in Catálogo Raisonné V.2 – Amadeo de Souza-Cardoso, pintura, A.A.a.F.C. Gulbenkian, Editor. Lisbon.Google Scholar
  42. 42.
    Montagner C (2015) The brushstroke and materials of Amadeo de Souza-Cardoso combined in an authentication tool, in Department of Conservation and Restoration, Faculdade de Ciências e Tecnologia - Universidade Nova de Lisboa: Lisbon.Google Scholar
  43. 43.
    Montagner C et al (2012) Unveiling the hand of a 19th Century artist with binary image classification and Bag-of-Features., in 19th International conference on Systems, Signals and Image (IWSSIP) IEEE: Austria. p. 201-204.Google Scholar
  44. 44.
    Montagner C et al (2013) Behind the surface - Hyperspectral image spectroscopy for artist authentication, in 12th International AIC Congress, AIC, Editor. p. 359-362Google Scholar
  45. 45.
    Nowak E, Jurie F, Triggs B (2006) Sampling strategies for Bag-of Features image classification, in European Conference on Computer Vision. Graz, Austria. p. 3954:490-503Google Scholar
  46. 46.
    Pelagotti A et al (2008) Multispectral imaging of paintings, a way to material identification. IEEE Signal Process Mag 36:27–36CrossRefGoogle Scholar
  47. 47.
    Pinto DP, Linhares JMM, Nascimento SMC (2008) Correlated color temperature preferred by observers for illumination of artistic paintings. J Opt Soc Am A 25:623–630CrossRefGoogle Scholar
  48. 48.
    Poggio T, Smale S (2003) The mathematics of learning: dealing with data. Notice Am Math Soc 50(5):537–544MathSciNetzbMATHGoogle Scholar
  49. 49.
    Robertson S (2004) Understanding Inverse Document Frequency: on theoretical arguments for IDF. J Doc 60(5):503–520CrossRefGoogle Scholar
  50. 50.
    Saleh B et al (2014) Toward automated discovery of artistic influence Multimedia Tools and Applications, p. 1-17Google Scholar
  51. 51.
    Savitzky A, Golay MJE (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627–1639CrossRefGoogle Scholar
  52. 52.
    Shen J (2009) Stochastic modelling western paintings for effective classification. Pattern Recogn 42:293–301CrossRefzbMATHGoogle Scholar
  53. 53.
    Stork DG (2006) Computer Vision, Image Analysis, and Master Art: Part 1. IEEE MultiMedia 13(3):16–20MathSciNetCrossRefGoogle Scholar
  54. 54.
    Stork DG, Duarte MF (2006) Computer Vision, Image Analysis, and Master Art: Part 3. MultiMedia, IEEE 14(1):14–18CrossRefGoogle Scholar
  55. 55.
    Stork DG, Johnson MK (2006) Computer Vision, Image Analysis, and Master Art: Part 2. MultiMedia, IEEE 13(4):12–17CrossRefGoogle Scholar
  56. 56.
    Taylor RP, Micolich AP, Jonas D (1999) Fractal analysis of Pollock drip paintings. Nature, 399(422).Google Scholar
  57. 57.
    Zhao Y (2008) Image segmentation and pigment mapping of cultural heritage based on spectral imaging, in PhD. Rochester, New York, United StatesGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Cristina Montagner
    • 1
    Email author
  • Rui Jesus
    • 4
  • Nuno Correia
    • 5
  • Márcia Vilarigues
    • 2
  • Rita Macedo
    • 3
  • Maria João Melo
    • 1
  1. 1.Requimte, LAQV, and Departamento de Conservação e Restauro, Faculdade de Ciências e TecnologiaUniversidade NOVA de LisboaMonte de CaparicaPortugal
  2. 2.VICARTE and Departamento de Conservação e Restauro, Faculdade de Ciências e TecnologiaUniversidade NOVA de LisboaMonte de CaparicaPortugal
  3. 3.IHA and Departamento de Conservação e Restauro, Faculdade de Ciências e TecnologiaUniversidade NOVA de LisboaMonte de CaparicaPortugal
  4. 4.Multimedia and Machine Learning GroupInstituto Superior de Engenharia de LisboaLisbonPortugal
  5. 5.NOVA-LINCS, Departamento de Informática, Faculdade de Ciências e TecnologiaUniversidade NOVA de LisboaLisbonPortugal

Personalised recommendations