Determining perceptually significant points on noisy boundary curves

Authors:
D. P. Illing;P. T. Fairney
Affiliations:
-;-
Venue:
Pattern Recognition Letters
Year:
1991

Citing 7
Cited 0

Using Polygons to Recognize and Locate Partially Occluded Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Model Construction and Shape Recognition from Occluding Contours

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstructing partially occluded object boundaries

Pattern Recognition Letters
Understanding Shape: Angles and Sides

IEEE Transactions on Computers
An Improved Method of Angle Detection on Digital Curves

IEEE Transactions on Computers
Angle Detection on Digital Curves

IEEE Transactions on Computers
Three-Dimensional Shape Analysis Using Local Shape Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.10

Visualization

Abstract

One method of describing the shape of objects in images is to locate points of maximum curvature on object boundaries. These are commonly believed to be the most perceptually significant points on digital curves. However, our work indicates that estimators of point curvature become highly unreliable in the presence of noise. Rather than attempting to locate such high curvature points directly, an approach is presented which searches for boundary segments which exhibit significant linearity; curvature discontinuities are then assigned to the junctions between boundary segments. The resulting object descriptions are much more stable in the presence of noise.