BIB-VERSION:: CS-TR-v2.0
          ID:: STAN//CS-TR-00-1631
       ENTRY:: April 14, 2000
ORGANIZATION:: Stanford University, Department of Computer Science
       TITLE:: Early Vision Using Distributions
        TYPE:: Thesis
        TYPE:: Technical Report
      AUTHOR:: Ruzon, Mark A.
        DATE:: April 2000
       PAGES:: 121
    ABSTRACT:: For over thirty years researchers in computer vision have
               been proposing new methods for performing ``early vision''
               tasks such as detecting edges and corners. One key element
               shared by most methods is that they represent local image
               neighborhoods as constant in color or intensity, with
               deviations modeled as noise. Due to computational
               considerations that encourage the use of small neighborhoods
               where this assumption holds, these methods remain popular.

               This research models a neighborhood as a distribution of
               colors. Our goal is to show that the increase in accuracy of
               this representation translates into higher-quality results
               for early vision tasks on difficult, natural images,
               especially as neighborhood size increases. We emphasize large
               neighborhoods because small ones often do not contain enough
               information. We emphasize color because it subsumes greyscale
               as an image range and because it limits the number of valid
               models we should consider; using only greyscale images allows
               assumptions that do not hold for color.

               We discuss distributions in the context of three related
               image boundary tasks: edge detection, corner detection, and
               estimating alpha, or the percentage with which two colors
               from two objects mix to form the color of a pixel at a
               boundary.
       NOTES:: [Adminitrivia V1/Prg/20000414]
         END:: STAN//CS-TR-00-1631