What is the color of chocolate? – Extracting color values of semantic expressions

Albrecht Lindner1, Nicolas Bonnier2, Sabine Süsstrunk1
1École Polytechnique Fédérale de Lausanne (Switzerland), 2Océ Print Logic Technologies (France)
Download paper

Play (20min)

Download: MP4 | MP3

We present a statistical framework to automatically determine an associated color for a given arbitrary semantic expression. The expression can not only be a color name but any word or character string. In addition to the color value, we are also able to compute the result’s significance, which determines how meaningful defining the color is for the expression. To demonstrate the framework’s strength we apply it to two well known tasks: assessing memory colors and finding the color values for a given color name (color naming). We emphasize that we solve these tasks fully automatic without any psychophysical experiment or human intervention. Further, we outline the potential of our automatic framework and in particular the significance for the imaging community.

You may also like:

  1. Extending SURF to the Color Domain
  2. Unsupervised Hierarchical Spatio-Colorimetric Classification for Color Image Segmentation
  3. Investigating human color harmony preferences using unsupervised machine learning
  4. Color correction of faded images using multi-scale gray world algorithm
  5. What is constant in color constancy?

  • Share
1 Star2 Stars3 Stars4 Stars5 Stars (No Ratings Yet)
Loading ... Loading ...