THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Using Directional Variance to Extract Curvees in Images, thus Improving Object Recognition in Clutter
UR > CS > Research > Vision > Publications > Using Directional Variance to Extract Curvees in Images, thus Improving Object Recognition in Clutter
pdf 249 KB
ps.gz 560 KB
ps 2.55 MB
@TechReport{Selinger:TR99b,
  author = 	 {Andrea Selinger and Randal C. Nelson},
  title = 	 {Using Directional Variance to Extract Curvees in Images, thus Improving Object Recognition in Clutter },
  institution =  {Comp. Sci. Dept. University of Rochester},
  year = 	 {1999},
  number = 	 {712},
  address = 	 {Rochester NY},
  month = 	 {April},
  abstract = {
In this report we describe a method for extracting curves from an image using directional pixel variances instead 
of gradient measures as low-level boundary evidence. The advantage of the variance over the image gradient is that
 we can accurately compute the direction of a local edge even if a sudden contrast change occurs in the background.
 This allows curves belonging to object contours to be followed more easily. We compared our method to a similar 
method based on the image gradient and we found that it obtains better results when run on synthetic and natural 
images. Our method also improved the performance of a contour-based 3D object recognition system in cluttered images.
}
}