Intelligent interactive image outlining using spline snakes

17 December 2002

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 1, 731-735 vol.1
https://doi.org/10.1109/acssc.1994.471548

Abstract

Outlining 2D shapes and image regions is often required in image manipulation and analysis. Most polygon and curve drawing tools in graphics do not use the knowledge of image intensities and its derivatives in guiding the outlining process, and hence are quite tedious and error prone. This paper presents a, fast interactive drawing tool based on a parametric spline formulation of snakes that exploits the underlying image intensities. Specifically, interactively specified contours are naturally attracted to strong image edges in the vicinity because spline snakes are designed to migrate to significant ridges in the gradient magnitude image. Furthermore, allowable stretching and bending can be controlled by minimizing explicitly the bending and stretching energies of the curve. Parameterization of spline snakes in terms of a limited number of control points yields a fast minimization solution thus enabling interactive rubber banding of the curve on the screen. This feedback allows users to quickly guide the snake on the desired path.

Keywords

This publication has 4 references indexed in Scilit:

Automatic recognition of brain regions from magnetic resonance images
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Fast algorithms for low-level vision
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1990
Snakes: Active contour models
International Journal of Computer Vision, 1988
Algorithms for Graphics and Image Processing
Published by Springer Nature ,1982