Image-Color-Analysis is a tool that analyzes the colors in a set of images and identifies color repetitions, resulting in a scale that informs us which colors are the most dominant and which appear the least frequently.
The output of the analysis is a color histogram (a graph that shows the frequency of colors in the images). By applying this analysis to multiple sets of images, the researcher can compare their color schemes. Thus, for example, a comparison can be made between various time periods.
Originally, this tool was developed for research on the national internet domain of the former Yugoslavia (.yu) during the Kosovo War, in order to map out shifts in the colors of the domain.
Image-Color-Analysis allows you to research big data easily, providing you with a bird’s-eye view of the data in order to gain new insights for your research.
You are invited to download the code and demo-data on GitHub, where you will also find a tutorial on how to install and use
Image-Color-Analysis.
The research and development of the tool was done by Dr. Anat Ben David and Adam Amram.
Possible Research Applications:
- Art History – color palettes of artists, periods, or places
- Public image of politicians
- Trends in commercial advertisements
- Social Media – analysis of profile images and gender
Publications:
Ben-David, A., Amram, A., & Bekkerman, R. (2018).
The colors of the national Web: visual data analysis of the historical Yugoslav Web domain. International Journal on Digital Lbraries, 19 (1), 95-106.