Color Semantics for Image Indexing

Martin Solli, Reiner Lenz
CGIV 2010: 5th European Conference on Colour in Graphics, Imaging, and Vision, page 353--358 - 2010
Download the publication : FULLTEXT01 (7).pdf [2.1Mo]  
We propose a color-based image descriptor that can be used for image indexing based on high-level semantic concepts. The descriptor is based on Kobayashi's Color Image Scale, which is a system that includes 130 basic colors combined in 1170 three-color combinations. Each combination is labeled with one of 180 high-level semantic concepts, like "elegant", "romantic", "provocative", etc. Moreover, words are located in a two-dimensional semantic space, and arranged into groups based on perceived similarity. From a modified approach for statistical analysis of images, involving transformations of ordinary RGB-histograms, a semantic image descriptor is derived, containing semantic information about both color combinations and single colors in the image. We show how the descriptor can be translated into different levels of semantic information, and used in indexing of multi-colored images. Intended applications are, for instance, image labeling and retrieval.

Images and movies

 

BibTex references

@InProceedings\{SL10,
  author       = "Solli, Martin and Lenz, Reiner",
  title        = "Color Semantics for Image Indexing",
  booktitle    = "CGIV 2010: 5th European Conference on Colour in Graphics, Imaging, and Vision",
  pages        = "353--358",
  year         = "2010",
  editor       = "Jussi Parkkinen, Timo Jääskeläinen, Theo Gevers, Alain Trémeau",
  publisher    = "IS\&T"
}

Author publication list