In this paper, we propose an improved gradient vector flow (GVF) snake to address the problem of poor convergence of GVF snake for the deep concavities in image segmentation. The major contribution is that new external force field is proposed combining the properties of GVF snake model and magnetostatic active contour (MAC) model, and the new external force field can help move the snake contour into deep boundary concavities. The proposed algorithm has been tested with experiments on various types of images, and significant improvement has been achieved in the convergence for approaching boundary concavities compared with the existing GVF snake method. © 2012 Springer Science+Business Media B.V.
CITATION STYLE
Chen, B., Zhao, J., Dong, E., Chen, J., Zhao, Y., & Yuan, Z. (2012). An improved GVF snake model using magnetostatic theory. In Lecture Notes in Electrical Engineering (Vol. 107 LNEE, pp. 431–440). https://doi.org/10.1007/978-94-007-1839-5_46
Mendeley helps you to discover research relevant for your work.