Abstract The paper presents a new external force field for active contour model, which is called CGVF (Curvature Gradient Vector Flow). CGVF improves on classical GVF by simplifying the formulas and increasing the item of curvature, so that the edge information can be kept well and diffused more quickly. Several standard images are used to segmenting experiments, and the results show that CGVF has obvious advantages compared with GVF in the iteration number of force field, the evolvement number of curve and the accuracy of convergence. In particular, when the initial curve is far from the edge of object, the convergence will be more superior.
A New Active Contour Model: Curvature Gradient Vector Flow
Computer Vision – ACCV 2006 ; 6 ; 633-642
Lecture Notes in Computer Science ; 3851 , 6
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Segmentation Result , Active Contour , Image Edge , Active Contour Model , Initial Curve Computer Science , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Image Processing and Computer Vision , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
A New Active Contour Model: Curvature Gradient Vector Flow
British Library Conference Proceedings | 2006
|Gradient Flows and Geometric Active Contour Models
British Library Conference Proceedings | 1995
|Gradient Vector Flow Fast Geodesic Active Contours
British Library Conference Proceedings | 2001
|Gradient vector flow fast geodesic active contours
IEEE | 2001
|Contour matching: a curvature-based approach
British Library Online Contents | 1998
|