Active contours with normally generalized gradient vector flow external force

被引:3
作者
赵恒博 [1 ]
刘利雄 [1 ]
张麒 [1 ]
姚宇华 [1 ]
刘宝 [1 ]
机构
[1] Beijing Key Laboratory of Intelligent Information Technology,School of Computer Science and Technology,Beijing Institute of Technology
基金
中国国家自然科学基金;
关键词
gradient vector flow; active contour; normal gradient vector flow; normally generalized gradient vector flow;
D O I
10.15918/j.jbit1004-0579.2012.02.009
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
Gradient vector flow(GVF) is an effective external force for active contours,but its isotropic nature handicaps its performance.The recently proposed gradient vector flow in the normal direction(NGVF) is anisotropic since it only keeps the diffusion along the normal direction of the isophotes;however,it has difficulties forcing a snake into long,thin boundary indentations.In this paper,a novel external force for active contours called normally generalized gradient vector flow(NGGVF) is proposed,which generalizes the NGVF formulation to include two spatially varying weighting functions.Consequently,the proposed NGGVF snake is anisotropic and would improve active contour convergence into long,thin boundary indentations while maintaining other desirable properties of the NGVF snake,such as enlarged capture range,initialization insensitivity and good convergence at concavities.The advantages on synthetic and real images are demonstrated.
引用
收藏
页码:240 / 245
页数:6
相关论文
共 50 条
[41]   EFFICIENT NUMERICAL SCHEMES FOR GRADIENT VECTOR FLOW [J].
Boukerroui, Djamal .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :4057-4060
[42]   Anisotropic diffusion analysis of gradient vector flow [J].
Ning J.-F. ;
Wu C.-K. ;
Jiang G. ;
Liu S.-G. .
Ruan Jian Xue Bao/Journal of Software, 2010, 21 (04) :612-619
[43]   Variational Segmentation of Vector-Valued Images With Gradient Vector Flow [J].
Jaouen, Vincent ;
Gonzalez, Paulo ;
Stute, Simon ;
Guilloteau, Denis ;
Chalon, Sylvie ;
Buvat, Irene ;
Tauber, Clovis .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (11) :4773-4785
[44]   SRAD, Optical Flow and Primitive Prior Based Active Contours for Echocardiography [J].
Hamou, Ali K. ;
El-Sakka, Mahmoud R. .
COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS: THEORY AND APPLICATIONS, 2010, 68 :158-171
[45]   ACTIVE CONTOURS WITH OPTICAL FLOW AND PRIMITIVE SHAPE PRIORS FOR ECHOCARDIOGRAPHIC IMAGERY [J].
Hamou, Ali K. ;
El-Sakka, Mahmoud R. .
IMAGAPP 2009: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON COMPUTER IMAGING THEORY AND APPLICATIONS, 2009, :111-118
[46]   Image Segmentation based on Improved Gradient Vector Flow [J].
Zhang, Hong ;
Feng, Lingzhi ;
Mu, Ying ;
You, Yuhu .
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, 2008, :765-+
[47]   Variational Curve Skeletons Using Gradient Vector Flow [J].
Hassouna, M. Sabry ;
Farag, Aly A. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (12) :2257-2274
[48]   A HIDDEN PROPERTY OF THE GRADIENT VECTOR FLOW DIFFUSION PROCESS [J].
Radulescu, Tiberiu ;
Buzuloiu, Vasile .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :2417-2420
[49]   Active contours driven by global and local weighted signed pressure force for image segmentation [J].
Han, Bin ;
Wu, Yiquan .
PATTERN RECOGNITION, 2019, 88 :715-728
[50]   A Fast External Force Field for Parametric Active Contour Segmentation [J].
De Vylder, Jonas ;
Douterloigne, Koen ;
Philips, Wilfried .
ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, PT I, 2010, 6474 :125-134