imagefluency-package: imagefluency: Image Statistics Based on Processing Fluency

imagefluency-packageR Documentation

imagefluency: Image Statistics Based on Processing Fluency

Description

logo

Get image statistics based on processing fluency theory. The functions provide scores for several basic aesthetic principles that facilitate fluent cognitive processing of images: contrast, complexity / simplicity, self-similarity, symmetry, and typicality. See Mayer & Landwehr (2018) \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1037/aca0000187")} and Mayer & Landwehr (2018) \Sexpr[results=rd]{tools:::Rd_expr_doi("10.31219/osf.io/gtbhw")} for the theoretical background of the methods.

Details

The main functions are:

  • img_contrast to get the visual contrast of an image

  • img_complexity to get the visual complexity of an image (equals 1 minus image simplicity)

  • img_self_similarity to get the visual self-similarity of an image

  • img_simplicity to get the visual simplicity of an image (equals 1 minus image complexity)

  • img_symmetry to get the vertical and horizontal symmetry of an image

  • img_typicality to get the visual typicality of a list of images relative to each other

Other helpful functions are:

  • img_read wrapper function to read images using readbitmap::read.bitmap

  • run_imagefluency to launch a Shiny app for an interactive demo of the main functions

  • rgb2gray to convert images from RGB into grayscale

Author(s)

Maintainer: Stefan Mayer stefan@mayer-de.com (ORCID)

References

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. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1037/aca0000187")}

Mayer, S. & Landwehr, J. R. (2018). Objective measures of design typicality. Design Studies, 54, 146–161. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.31219/osf.io/gtbhw")}

See Also

Useful links:


stm/imagefluency documentation built on Feb. 27, 2024, 9:29 a.m.