Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions
Abstract
Whereas one part of art history is a history of inventions, the other part is a history of transfer, of variations and copies. Art history wants to understand the differences between these, in order to learn about artistic choices and stylistic variations. In this paper we develop a method that can detect variations between artworks and their reproductions, in particular deformations in shape. Specifically, we present a novel algorithm which automatically finds regions which share the same transformation between original and its reproduction. We do this by minimizing an energy function which measures the distortion between local transformations of the shape. Thereby, the grouping and registration problem are addressed jointly and model complexity is obtained using a stability analysis. Moreover, our method allows art historians to evaluate the exactness of a copy by identifying which contours where considered relevant to copy. The proposed shape-based approach thus helps to investigate art through the art of reproduction.
Cite
Text
Kuhn et al. "Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33863-2_59Markdown
[Kuhn et al. "Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/kuhn2012eccv-shaping/) doi:10.1007/978-3-642-33863-2_59BibTeX
@inproceedings{kuhn2012eccv-shaping,
title = {{Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions}},
author = {Kuhn, Juan Antonio Monroy and Bell, Peter and Ommer, Björn},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {571-580},
doi = {10.1007/978-3-642-33863-2_59},
url = {https://mlanthology.org/eccv/2012/kuhn2012eccv-shaping/}
}