Abstract
Increasing digital art has, without a doubt democratized the access to art content to the public at large. It has had, however, resulted in an inadvertent growing number of forgeries and misinformation around art content. In this work, we employ convolutional network-based strategies to identify and classify art-related digital artifacts. Firstly, van Gogh paintings are used to explore and refine strategies capable of discriminating the brushstroke pattern of van Gogh. We achieve significant performance improvements over the VGDB-2016 dataset, while also increasing class-balanced accuracy when compared to previous results in the same set. In a second phase, we collect two new sets and perform cross-dataset evaluation to demonstrate that our solution generalizes well to painting recaptures with varying resolution, sizes and sources, while performing fairly well against unseen high-resolution scans of paintings. Finally, we propose a strategy for painting authentication that combines results of multiple recaptures.
Research funded by CAPES, CNPq, Microsoft Research Latin America and FAPESP (Grant #2017/12646-3).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bar, Y., Levy, N., Wolf, L.: Classification of artistic styles using binarized features derived from a deep neural network. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 71–84. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16178-5_5
Bi, Y., Xue, B., Zhang, M.: An effective feature learning approach using genetic programming with image descriptors for image classification. IEEE Comput. Intell. Mag. 15(2), 65–77 (2020)
Folego, G., Gomes, O., Rocha, A.: From impressionism to expressionism: automatically identifying van Gogh’s paintings. In: IEEE International Conference on Image Processing (ICIP), pp. 141–145 (2016)
Johnson, C.R., et al.: Image processing for artist identification. IEEE Signal Process. Mag. 25(4), 37–48 (2008)
Liu, H., Chan, R.H., Yao, Y.: Geometric tight frame based stylometry for art authentication of van Gogh paintings. Appl. Comput. Harmon. Anal. 41(2), 590–602 (2016)
Qi, H., Hughes, S.: A new method for visual stylometry on impressionist paintings. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2036–2039 (2011)
Qi, H., Taeb, A., Hughes, S.M.: Visual stylometry using background selection and wavelet-HMT-based Fisher information distances for attribution and dating of impressionist paintings. Signal Process. 93(3), 541–553 (2013)
Sandoval, C., Pirogova, E., Lech, M.: Two-stage deep learning approach to the classification of fine-art paintings. IEEE Access 7, 41770–41781 (2019)
Shamir, L., Macura, T., Orlov, N., Eckley, D., Goldberg, I.: Impressionism, expressionism, surrealism: automated recognition of painters and schools of art. ACM Trans. Appl. Percept. 7, 8:1–8:17 (2010)
Yang, H., Min, K.: Classification of basic artistic media based on a deep convolutional approach. Vis. Comput. 36(3), 559–578 (2019). https://doi.org/10.1007/s00371-019-01641-6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
David, L.O., Pedrini, H., Dias, Z., Rocha, A. (2021). Authentication of Vincent van Gogh’s Work. In: Tsapatsoulis, N., Panayides, A., Theocharides, T., Lanitis, A., Pattichis, C., Vento, M. (eds) Computer Analysis of Images and Patterns. CAIP 2021. Lecture Notes in Computer Science(), vol 13053. Springer, Cham. https://doi.org/10.1007/978-3-030-89131-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-89131-2_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89130-5
Online ISBN: 978-3-030-89131-2
eBook Packages: Computer ScienceComputer Science (R0)