imagefluency: Image Statistics Based on Processing Fluency


imagefluency is a simple R package for image fluency scores. The package allows to get scores for several basic aesthetic principles that facilitate fluent cognitive processing of images. If you want to try it out before installing, you can find an interactive Shiny app here (alpha version).

The main functions are:

Other helpful functions are:

  • img_read() wrapper function to read images into R using read.bitmap() from the readbitmap package
  • rgb2gray() convert images from RGB into grayscale (might speed up computation)
  • run_imagefluency() to launch a Shiny app locally on your computer for an interactive demo of the main functions

The main author is Stefan Mayer.


You can install the current stable version from CRAN.


To download the latest development version from Github use the install_github function of the remotes package.

# install remotes if necessary
if (!require('remotes')) install.packages('remotes')
# install imagefluency from github

Optionally, if you have rmarkdown installed, you can also have your system build the the vignettes when downloading from GitHub.

# install from github with vignettes (needs rmarkdown installed)
remotes::install_github('stm/imagefluency', build_vignettes = TRUE)

Use the following link to report bugs/issues:

Example usage

# visual contrast
# example image file (from package): bike.jpg
bike_location <- system.file('example_images', 'bike.jpg', package = 'imagefluency')
# read image from file
bike <- img_read(bike_location)
# get contrast

# visual symmetry
# read image
rails <- img_read(system.file('example_images', 'rails.jpg', package = 'imagefluency'))
# get only vertical symmetry
img_symmetry(rails, horizontal = FALSE)


See the getting started vignette for a detailed introduction and the reference page for details on each function.

If you are analyzing a larger number of images, make sure to read the tutorial on how to analyze multiple images at once.


To cite imagefluency in publications use:

Mayer, S. (2021). imagefluency: Image Statistics Based on Processing Fluency. R package version 0.2.4. doi: 10.5281/zenodo.5614666

A BibTeX entry is:

  author       = {Stefan Mayer},
  title        = {imagefluency: Image Statistics Based on Processing Fluency},
  year         = 2021,
  version      = {0.2.4},
  doi          = {10.5281/zenodo.5614666},
  url          = {}


The img_complexity function relies on the packages R.utils and magick. The img_self_similarity function relies on the packages OpenImageR, pracma, and quadprog. The img_read function relies on the readbitmap package. The run_imagefluency shiny app depends on shiny.

Further references

To learn more about the different image fluency metrics, see the following publications:

  • Mayer, S. & Landwehr, J, R. (2018). Quantifying Visual Aesthetics Based on Processing Fluency Theory: Four Algorithmic Measures for Antecedents of Aesthetic Preferences. Psychology of Aesthetics, Creativity, and the Arts, 12(4), 399–431. doi: 10.1037/aca0000187

  • Mayer, S. & Landwehr, J. R. (2018). Objective measures of design typicality. Design Studies, 54, 146–161. doi: 10.1016/j.destud.2017.09.004

Code of Conduct

Please note that this project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.