A network for multiscale image segmentation
Open Access
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2565-2568 vol.3
- https://doi.org/10.1109/iscas.1988.15465
Abstract
Detecting edges of objects in their images is a basic problem in computational vision. The authors present the major ideas behind the use of scale space and anisotropic diffusion for edge detection, show that anisotropic diffusion can enhance edges, suggest a network implementation of anisotropic diffusion, and provide design criteria for obtaining networks performing scale space and edge detection. The results of a software implementation are shown.<>Keywords
This publication has 7 references indexed in Scilit:
- Scale-space and edge detection using anisotropic diffusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Deblurring gaussian blurComputer Vision, Graphics, and Image Processing, 1986
- Scaling Theorems for Zero CrossingsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- Uniqueness of the Gaussian Kernel for Scale-Space FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- The structure of imagesBiological Cybernetics, 1984
- Partial Differential EquationsPublished by Springer Nature ,1982
- Edge and Curve Detection for Visual Scene AnalysisIEEE Transactions on Computers, 1971