Automatic Color Palette Creation from Words
2013. IS&T 21st Color and Imaging Conference , Albuquerque, New Mexico , November 4-8, 2013. p. 69-74.
Link semantics to image content
Using a statistical test we compute the significance of color values for a given semantic expression. This figure shows which parts of an HSV color histogram are significantly linked to the keyword grass.
Left: HS-plane of an HSV histogram (V=0.5). Right: Significance scores for the keyword grass for each histogram bin.
We place 5 colors in the HSV space that maximize the palette’s significance ans satisfy a given hue template. Here is an example palette for the example of grass.
The automatically extracted can also be ranked with the significance score. The below figure shows an example for the keyword cherry. Palettes for four different hue templates (indicated on the left of the palettes) have been created and the results are ranked by their significance scores (numbers to the left). Palettes with a higher significance score are a better representation fo the underlying semantic concept.