Multi-scale edge detection with bilateral filtering in spiral architecture

Authors:
Qimei Hu;Xiangjian He;Jun Zhou
Affiliations:
University of Technology, Sydney, Australia;University of Technology, Sydney, Australia;University of Technology, Sydney, Australia
Venue:
VIP '05 Proceedings of the Pan-Sydney area workshop on Visual information processing
Year:
2004

Citing 7
Cited 2

Practical algorithms for image analysis: description, examples, and code

Practical algorithms for image analysis: description, examples, and code
Digital Image Processing: PIKS Inside

Digital Image Processing: PIKS Inside
Numerical Methods for DSP Systems in C with 3.5 Disk

Numerical Methods for DSP Systems in C with 3.5 Disk
Scale-Space Theory in Computer Vision

Scale-Space Theory in Computer Vision
An Introduction to Digital Image Processing

An Introduction to Digital Image Processing
Bilateral Filtering for Gray and Color Images

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Machine Vision: Theory, Algorithms, Practicalities

Machine Vision: Theory, Algorithms, Practicalities

An adaptive window mechanism for image smoothing

Computer Vision and Image Understanding
Multi-scale and first derivative analysis for edge detection in TEM images

ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Real images are often corrupted by noise from various sources. Bilateral filtering is a nonlinear filter that considers intensity variations as well as spatial closeness in the noise smoothing process. It has been demonstrated to have a better edge-preserving quality than linear filters in certain applications. This paper presents the new edge detection algorithm with the application of a bilateral filter in Gaussian form in Spiral Architecture. Spiral Architecture is a relatively new concept in the area of image representation and offers distinctive advantages. The approach to edge detection is multi-scale. Edge maps of the original image and its successively smoothed versions are used to produce the final edge map.