Local estimation of Gaussian-based edge enhancement filters using Fourier analysis

Authors:
Bin Wang;D. M. Rose;Aly A. Farag;Edward J. Delp
Affiliations:
Engineering Mathematics & Computer Science Dept., Speed Scientific School, University of Louisville, Louisville, KY;Engineering Mathematics & Computer Science Dept., Speed Scientific School, University of Louisville, Louisville, KY;Engineering Mathematics & Computer Science Dept., Speed Scientific School, University of Louisville, Louisville, KY;Computer Vision & Image Processing Lab., School of Electrical Engineering, Purdue University, West Lafayette, IN
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
Year:
1993

Citing 3
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Authenticating Edges Produced by Zero-Crossing Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital image processing (2nd ed.)

Digital image processing (2nd ed.)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Edge-based image segmentation is a two-stage process; edge enhancement followed by edge linking. Modern approaches for edge enhancement use either the gradient of the Gaussian operator (∇G) or the Laplacian of the Gaussian operator (∇2G). Both operators maximize the energy of the output and both can be performed as the cascade of two operations: a filtering operation with a Gaussian filter followed by a differentiation operation (∇ or ∇2). The Gaussian filter is specified by its standard deviation σ The filter's spatial support is a function of σ. In this paper, an estimation procedure for σ is described using Fourier analysis.