The geodesic active contour (GAC) model has been widely used due to the high precision of edge detection and the continuity of boundaries. However, compared to the gradient vector flow (GVF) field, it usually has poor performance in the object boundaries with concave shape. In this paper, the improvements that integrate the good performance of the GAC model and the GVF field are described in detail and the GAC_GVF&B model combining the GAC model with the GVF field and a balloon force is proposed. The experimental results demonstrate that the proposed method is insensitive to the positions of initial curves and can segment complex-shape or multi-objects images correctly with higher convergence.
KassM.WitkinA., and TerzopoulosD., Snakes: Active contour models, Int. J. Comput. Vision1(1988), pp. 321–331.
2.
ParkH.SchoepflinY., and KimT., Active contour model with gradient directional information: Directional snake, IEEE Trans. Circuit Syst. Video Technol.11(2) (2001), pp. 252–256.
3.
ParkH.K., and ChungM.J., External force of snake: Virtual electric field, Electron. Lett.38 (24) (2002), pp. 1500–1502.
4.
ShihF.Y., and ZhangK., Locating object contours in complex background using improved snakes, Comput. Vision Imaging102(2) (2006), pp. 93–98.
5.
SumK.W., and CheungP.Y.S., Boundary vector field for parametric active contours, Pattern Recognit.40(6) (2007), pp. 1635–1645.
6.
XiangY.ChungA.C.S., and YeJ., An active contour model for image segmentation based on elastic interaction. J. Comput. Phys.219(1) (2006), pp. 455–476.
7.
XieX., and MirmehdiM., Magnetostatic field for the active contour model: A study in convergence, Proceedings of the 17th British Machine Vision Conference, 2006.
8.
CohenL.D., On active contour models and balloons. CVGIP: Image Understand, 53(2) (1991), pp. 211–218.
9.
CohenL.D., and CohenI., Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans. Pattern Anal. Machine Intell.15(1993), pp. 1131–1147.
10.
XuC., and PrinceJ.L., Gradient vector flow: A new external force for snakes, IEEE Proc. Conf. on Comput. Vis. Patt. Recog. (CVPR), 1997.
11.
XuC., and PrinceJ.L., Generalized gradient vector flow external forces for active contours. Signal Process.71(1998a), pp. 131–139.
12.
XuC., and PrinceJ.L., Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process.7(3) (1998b), pp. 359–369.
13.
NingJ.WuC., and LiuS., NGVF: An improved external force field for active contour model. Pattern Recognition Letters, 28(2007): Pp. 58–63.
14.
GuoY.WangM., and LaiC., An improved GAC Model Combining with GNGVF, DCABES, 2011.
15.
GuoY., Image Segmentation Method Based on GAC Model Combined with GVF, Master thesis, Fuzhou University, 2012.
16.
CasellesV.KimmelR., and SapiroG., Geodesic active contours, International Journal of Computer Vision, 22(1) (1997), pp. 61–79.
17.
SethianJ.A., Evolution, Implementation and application of level set and fast marching methods for advancing fronts. J. Comput. Phys, 169(2) (2001), pp. 503–555.
18.
ZhuG.ZhangS., and ZengQ., Gradient vector flow active contours with prior directional information. Pattern Recognition Letters, 31(2010), pp. 845–856.
19.
ZhangB.SuY.XuY., and ZhangS., An Adaptive Geodesic Active Contour Model.ICNC, 2010.
20.
ParagiosN.Mellina-GottardoO., and RameshV., Gradient vector flow fast geodesic active contours [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 26(3) (2004), pp. 402–407.
21.
ZhuG., Image Segmentation based on Active Contour Model, Ph.D. diss., Harbin Institute of Technology, 2007.
