Discerning the painter’s hand: machine learning on surface topography
Abstract Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art students. The paintings were scanned using a...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
SpringerOpen
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/7b411a738efc4086bfe7f7f9ff078349 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:7b411a738efc4086bfe7f7f9ff078349 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:7b411a738efc4086bfe7f7f9ff0783492021-11-14T12:10:59ZDiscerning the painter’s hand: machine learning on surface topography10.1186/s40494-021-00618-w2050-7445https://doaj.org/article/7b411a738efc4086bfe7f7f9ff0783492021-11-01T00:00:00Zhttps://doi.org/10.1186/s40494-021-00618-whttps://doaj.org/toc/2050-7445Abstract Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art students. The paintings were scanned using a chromatic confocal optical profilometer to produce surface height data. The surface data were divided into virtual patches and used to train an ensemble of convolutional neural networks (CNNs) for attribution. Over a range of square patch sizes from 0.5 to 60 mm, the resulting attribution was found to be 60–96% accurate, and, when comparing regions of different color, was nearly twice as accurate as CNNs using color images of the paintings. Remarkably, short length scales, even as small as a bristle diameter, were the key to reliably distinguishing among artists. These results show promise for real-world attribution, particularly in the case of workshop practice.F. JiM. S. McMasterS. SchwabG. SinghL. N. SmithS. AdhikariM. O’DwyerF. SayedA. IngrisanoD. YoderE. S. BolmanI. T. MartinM. HinczewskiK. D. SingerSpringerOpenarticleTopographyMachine intelligenceConvolutional neural networks (CNNs)AttributionFine ArtsNAnalytical chemistryQD71-142ENHeritage Science, Vol 9, Iss 1, Pp 1-11 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Topography Machine intelligence Convolutional neural networks (CNNs) Attribution Fine Arts N Analytical chemistry QD71-142 |
| spellingShingle |
Topography Machine intelligence Convolutional neural networks (CNNs) Attribution Fine Arts N Analytical chemistry QD71-142 F. Ji M. S. McMaster S. Schwab G. Singh L. N. Smith S. Adhikari M. O’Dwyer F. Sayed A. Ingrisano D. Yoder E. S. Bolman I. T. Martin M. Hinczewski K. D. Singer Discerning the painter’s hand: machine learning on surface topography |
| description |
Abstract Attribution of paintings is a critical problem in art history. This study extends machine learning analysis to surface topography of painted works. A controlled study of positive attribution was designed with paintings produced by a class of art students. The paintings were scanned using a chromatic confocal optical profilometer to produce surface height data. The surface data were divided into virtual patches and used to train an ensemble of convolutional neural networks (CNNs) for attribution. Over a range of square patch sizes from 0.5 to 60 mm, the resulting attribution was found to be 60–96% accurate, and, when comparing regions of different color, was nearly twice as accurate as CNNs using color images of the paintings. Remarkably, short length scales, even as small as a bristle diameter, were the key to reliably distinguishing among artists. These results show promise for real-world attribution, particularly in the case of workshop practice. |
| format |
article |
| author |
F. Ji M. S. McMaster S. Schwab G. Singh L. N. Smith S. Adhikari M. O’Dwyer F. Sayed A. Ingrisano D. Yoder E. S. Bolman I. T. Martin M. Hinczewski K. D. Singer |
| author_facet |
F. Ji M. S. McMaster S. Schwab G. Singh L. N. Smith S. Adhikari M. O’Dwyer F. Sayed A. Ingrisano D. Yoder E. S. Bolman I. T. Martin M. Hinczewski K. D. Singer |
| author_sort |
F. Ji |
| title |
Discerning the painter’s hand: machine learning on surface topography |
| title_short |
Discerning the painter’s hand: machine learning on surface topography |
| title_full |
Discerning the painter’s hand: machine learning on surface topography |
| title_fullStr |
Discerning the painter’s hand: machine learning on surface topography |
| title_full_unstemmed |
Discerning the painter’s hand: machine learning on surface topography |
| title_sort |
discerning the painter’s hand: machine learning on surface topography |
| publisher |
SpringerOpen |
| publishDate |
2021 |
| url |
https://doaj.org/article/7b411a738efc4086bfe7f7f9ff078349 |
| work_keys_str_mv |
AT fji discerningthepaintershandmachinelearningonsurfacetopography AT msmcmaster discerningthepaintershandmachinelearningonsurfacetopography AT sschwab discerningthepaintershandmachinelearningonsurfacetopography AT gsingh discerningthepaintershandmachinelearningonsurfacetopography AT lnsmith discerningthepaintershandmachinelearningonsurfacetopography AT sadhikari discerningthepaintershandmachinelearningonsurfacetopography AT modwyer discerningthepaintershandmachinelearningonsurfacetopography AT fsayed discerningthepaintershandmachinelearningonsurfacetopography AT aingrisano discerningthepaintershandmachinelearningonsurfacetopography AT dyoder discerningthepaintershandmachinelearningonsurfacetopography AT esbolman discerningthepaintershandmachinelearningonsurfacetopography AT itmartin discerningthepaintershandmachinelearningonsurfacetopography AT mhinczewski discerningthepaintershandmachinelearningonsurfacetopography AT kdsinger discerningthepaintershandmachinelearningonsurfacetopography |
| _version_ |
1718429412242751488 |