Paper
29 March 1989 Boundaries As Unpredictable Discontinuities
Richard J. Gleeson, Josef Skrzypek
Author Affiliations +
Abstract
A large part of the information content of an image is conveyed by the location of pixels that determine the boundaries between different segments. In absence of prior knowledge about objects in the scene, it is impossible to predict where the edges will occur. The gray levels at locations away from boundaries are often highly correlated. They can be estimated from the values of nearby locations using assumptions based on our knowledge of the physical laws governing reflections from surfaces. Boundaries occur at points of essentially infinite variation. At these points corresponding gray levels result from summing energy reflected by two different regions and cannot be easily estimated from the values at nearby pixels. In this sense gray level values at discontinuities are less predictable.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Richard J. Gleeson and Josef Skrzypek "Boundaries As Unpredictable Discontinuities", Proc. SPIE 1076, Image Understanding and the Man-Machine Interface II, (29 March 1989); https://doi.org/10.1117/12.952689
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Edge detection

Error analysis

Image understanding

Detection and tracking algorithms

Interfaces

Image processing

Image segmentation

RELATED CONTENT

Using physical color models in 3-D machine vision
Proceedings of SPIE (August 01 1990)
Optimal algorithm for detecting two-dimensional images
Proceedings of SPIE (February 27 1996)
Image registration based on geometric pattern matching
Proceedings of SPIE (November 15 2011)
Using color to segment images of 3-D scenes
Proceedings of SPIE (March 01 1991)

Back to Top