The Distant Viewing Toolkit is a Python package that facilitates the computational analysis of still and moving images. The most recent version of the package focuses on providing a minimal set of functions that require only a small set of dependencies. Examples of how to make use of the toolkit are given in the following section.
For more information about setting up the toolkit on your own machine, please see INSTALL.md. More information about the toolkit and project is available on the following pages:
- Example analysis using aggregated metadata: "Visual Style in Two Network Era Sitcoms"
- Theory of the project: "Distant Viewing: Analyzing Large Visual Corpora."
- Software Whitepaper: A Python Package for the Analysis of Visual Culture
If you have any trouble using the toolkit, please open a GitHub issue. If you have additional questions or are interested in collaborating, please contact us at tarnold2@richmond.edu and ltilton@richmond.edu.
If you are interested in learning more about application of computer vision and the distant viewing toolkit to humanities applications, we offer a self-guided tutorial through the following Google Colab notebooks. These can be run for free by anyone with a Google account:
- Distant Viewing Tutorial 1: Movie Posters and Color Analysis: [colab], [slides], [notebook], [chapter]
- Distant Viewing Tutorial 2: Network-Era Sitcoms and Visual Style: [colab], [slides], [notebook], [chapter]
A shorted demo of the toolkit is also available in the following Google Colab notebook:
- Distant Viewing Toolkit Demo: [colab]
Unlike the tutorials, the short demo assumes some prior knowledge of Python. While a background in machine learning or computer vision is not needed, the methods are presented with minimal motivation.
The Distant Viewing Toolkit is supported by the National Endowment for the Humanities through a Digital Humanities Advancement Grant.
If you make use of the toolkit in your work, please cite the relevant papers describing the tool and its application to the study of visual culture:
@article{,
title = "Distant Viewing: Analyzing Large Visual Corpora",
author = "Arnold, Taylor B and Tilton, Lauren",
journal = "Digital Scholarship in the Humanities",
year = "2019",
doi = "10.1093/digitalsh/fqz013",
url = "http://dx.doi.org/10.1093/digitalsh/fqz013"
}
@article{,
title = "Visual Style in Two Network Era Sitcoms",
author = "Arnold, Taylor B and Tilton, Lauren and Berke, Annie",
journal = "Cultural Analytics",
year = "2019",
doi = "10.22148/16.043",
url = "http://dx.doi.org/10.22148/16.043"
}
Contributions, including bug fixes and new features, to the toolkit are welcome. When contributing to this repository, please first discuss the change you wish to make via a GitHub issue or email with the maintainers of this repository before making a change. Small bug fixes can be given directly as pull requests.