Loop-free snakes for highly irregular object shapes

Authors:
Lilian Ji;Hong Yan
Affiliations:
School of Electrical and Information Engineering, The University of Sydney, Box 071, Bld. 703, Darlington, Sydney, NSW, Australia;School of Electrical and Information Engineering, The University of Sydney, Box 071, Bld. 703, Darlington, Sydney, NSW, Australia
Venue:
Pattern Recognition Letters
Year:
2002

Citing 10
Cited 1

On active contour models and balloons

CVGIP: Image Understanding
A fast algorithm for active contours and curvature estimation

CVGIP: Image Understanding
Shape Modeling with Front Propagation: A Level Set Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geodesic Active Contours

International Journal of Computer Vision
A contour detection method: initialization and contour model

Pattern Recognition Letters
A new method for ROI extraction from motion affected MR images based on suppression of artifacts in the image background

Signal Processing
Image segmentation by reaction-diffusion bubbles

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Statistical Approach to Snakes for Bimodal and Trimodal Imagery

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Geodesic Active Regions for Supervised Texture Segmentation

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing

Force field analysis snake: an improved parametric active contour model

Pattern Recognition Letters

Quantified Score

Hi-index	0.11

Visualization

Abstract

'Snakes' are an effective approach to image segmentation. However, self-looping is a common problem that can cause segmentation failure of snakes in the recovery of highly irregular object shapes, such as in long tube-like shapes, sharp corners or deep concave/convex shapes. This paper introduces the notion of loop-free snakes that can quickly and effectively remove all self-loops during their evolution, consistently deforming and conforming to complicated shapes of target objects. The proposed snakes are less sensitive to their initial contour condition, are resilient to their inconsistent parameter settings in a Certain degree and require low computing cost in terms of both computation time and storage. Experiments are conducted to segment real images with encouraging results.