Jean-Christophe Baillie Certainty Color Maps Compared to Histograms. February 2002.

Sony CSL authors: Jean-Christophe Baillie

Abstract

We present a new segmentation algorithm based on probabilistic histograms and introduce certainty calculus and certainty color maps to solve the difficult problem o f histogram separation. This new method is then compared to simple histogram and normalized histogram techniques. Using a set of experiments designed to measure the quality of segmentation, we have shown that certainty color maps is a much more accurate approach than histograms, especially when histogram separation in necessary.

Keywords: histograms, certainty color maps, segmentation, computer vision

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@MISC { baillie:02b, AUTHOR="Jean-Christophe Baillie", MONTH="February", SCHOOL="Université Paris VI", TITLE="Certainty Color Maps Compared to Histograms", YEAR="2002", }