Back to articles
Volume: 3 | Article ID: art00013
Fuzzy Color-Based Semantic Characterization of Animation Movies
  DOI :  10.2352/CGIV.2006.3.1.art00013  Published OnlineJanuary 2006

In this paper a fuzzy statistical color–based approach for semantic characterization of animation movies is proposed. Color is a major feature of animation movies: each movie has its own color distribution. Deriving semantic information about the used color artistry concepts or about the sensation induced by the movie's color distribution should be an ideal analysis-tool for the animation experts. First, the movie is divided into shots and a movie abstract is then automatically generated. Color reduction is applied on each retained frame using an error diffusion algorithm with a predefined color palette. Then, a global weighted color histogram of the movie is computed by taking into account each shot relevance. It serves as a basis of computation for relevant color-based statistics, such as the elementary colors distribution or the light/dark color ratios. Using a fuzzy representation, meaningful color–based semantic information is then derived from the obtained parameters, namely: light–dark contrast, cold-warm contrast and contrast of saturation schemes, the color variations/diversity and the adjacent/complementary colors. The proposed approach was tested on several animation movies.

Subject Areas :
Views 11
Downloads 0
 articleview.views 11
 articleview.downloads 0
  Cite this article 

Bogdan Ionescu, Patrick Lambert, Didier Coquin, Vasile Buzuloiu, "Fuzzy Color-Based Semantic Characterization of Animation Moviesin Proc. IS&T CGIV 2006 3rd European Conf. on Colour in Graphics, Imaging, and Vision,  2006,  pp 65 - 69,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2006
Conference on Colour in Graphics, Imaging, and Vision
conf colour graph imag vis
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA