Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
An Open Access Platform for Analyzing Artistic Style Using Semantic Workflows
verfasst von : Ricky J. Sethi, Catherine A. Buell, William P. Seeley, Swaroop Krothapalli
Erschienen in: Web Services – ICWS 2018
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
We have created an open access online platform for using semantic workflows to analyze artistic style in paintings. We have implemented workflows for both standard computer vision image processing techniques and state-of-the-art methods such as convolutional neural networks to analyze images. These workflows can be used online by non-experts without needing any technical knowledge other than being able to use a browser.
We designed three artistically-relevant features to aid in the quantification of artistic style: the Discrete Tonal Measure, Discrete Variational Measure, and Convolutional Style Measure. These quantitative features can provide clues to the artistic elements that enable art scholars to categorize works as belonging to different artistic styles. We also created two new datasets of manually curated artworks selected especially for evaluating artistic style: one based on the school of art to which artists belong (Impressionism vs Hudson River) and one based on the medium used by a specific artist (tempera vs watercolors). Finally, we present an initial evaluation of these datasets and features for classifying paintings and also show results of a user study workshop for conducting such analyses online by humanities researchers, students, and professionals.