Share Email Print

Proceedings Paper

Boundary Detection In A Texture-Based Vision System
Author(s): L. Hong; D. Brzakovie; A. Liakopoulos
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new method for boundary estimation in textured images is described in this paper. This method aims at segmentation of images that contain 3-dimensional textured scenes. The essence of the method is estimation of boundaries between regions in an image, that contain homogeneous texture, us-ing a linear recursive filter and a random search procedure. Boundaries are modeled by the cubic B-spline functions and the measurement model employs the measures of inertia and energy calculated from co-occurrence matrices. The results obtained are very satisfactory. The method is an integral part of a 3-dimensional vision system that determines dis-tances to various obstacles placed on textured surfaces.

Paper Details

Date Published: 19 October 1987
PDF: 6 pages
Proc. SPIE 0856, IECON '87: Industrial Applications of Robotics & Machine Vision, (19 October 1987); doi: 10.1117/12.943025
Show Author Affiliations
L. Hong, University of Tennessee (United States)
D. Brzakovie, University of Tennessee (United States)
A. Liakopoulos, System Dynamics Inc. (United States)

Published in SPIE Proceedings Vol. 0856:
IECON '87: Industrial Applications of Robotics & Machine Vision
Abe Abramovich, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?