Paper
11 August 1995 Autonomous extraction of shape and topology of contours using geometry-driven diffusion and optimization of functionals
Eric J. Pauwels, Peter Fiddelaers, Luc J. Van Gool, Andre J. Oosterlinck
Author Affiliations +
Abstract
We show how geometry-driven diffusion based on the Nordstrom-functional can be used to crystallize the geometric content of a closed contour by simultaneously suppressing noise while enhancing the salient features. Furthermore, we propose a robust and highly parallelizable method that will automatically group edge-segments to produce a set of fully connected contours. The result could be used e.g., as input for recognition programs based on aspect graphs, or as a good initial guess for snakes and active contours.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Eric J. Pauwels, Peter Fiddelaers, Luc J. Van Gool, and Andre J. Oosterlinck "Autonomous extraction of shape and topology of contours using geometry-driven diffusion and optimization of functionals", Proc. SPIE 2573, Vision Geometry IV, (11 August 1995); https://doi.org/10.1117/12.216428
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Diffusion

Image segmentation

Distance measurement

Crystals

Reconstruction algorithms

Stochastic processes

Clocks

Back to Top