A discrete dynamic contour model

TLDR

The study develops a discrete dynamic contour model for 2‑D images that includes solutions to prevent shrinking and vertex clustering common in existing active contour methods. The model consists of connected vertices whose internal energy depends on local curvature and external energy on image features, and it iteratively adjusts the contour via energy minimization until a local minimum is reached. The method produces reproducible contour approximations and successfully applies to both computer‑generated and clinical images, demonstrating the effectiveness of the deformation‑avoidance solutions.

Abstract

A discrete dynamic model for defining contours in 2-D images is developed. The structure of this model is a set of connected vertices. With a minimum of interaction, an initial contour model can be defined, which is then automatically modified by an energy minimizing process. The internal energy of the model depends on local contour curvature, while the external energy is derived from image features. Solutions are presented to avoid undesirable deformation effects, like shrinking and vertex clustering, which are common in existing active contour models. The deformation process stops when a local minimum of the energy function is reached. The final shape of the model is a reproducible approximation of the desired contour. Results of applying the method to computer-generated images, as well as clinical images, are presented.