Homogeneity induced inertial snake with application to medical image segmentation

Snakes or active contour model is used extensively for image segmentation in varied fields. However, some of its limitations restrict its use in many fields. This paper proposes a new homogeneity controlled inertial force driven energy minimizing spline for tracking object contours. An inertial force apart from the first and second order continuity forces controls the proposed spline. The inertial force is in turn guided by a homogeneity criteria, defined based on the initial location of the spline. This new force field pushes the snake through the concavities and also against weak edge forces. A greedy snake has been used for computation of the energy minimizing spline. The algorithm has been tested on phantoms and ultrasound images as well. This algorithm can even be extended for textured image segmentation and many other areas, where the application of snake is restricted by its inability to conform to true edges or converge to concavities.