全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种新的用于医学图像分割的几何活动轮廊模型

Keywords: 医学图像分割几何活动轮廊Level-Set理论边缘提取噪声虚假边缘

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出一种新的几何活动轮廊模型对医学图像进行分割.首先,我们对几何活动轮廊模型中吸引力场进行正则化,扩大目标轮廊边缘对的轮廊曲线的吸引力范围,增加轮廊曲线搜寻凹轮廊的能力.然后,采用多尺度模型增加对边缘提取的精确度.将正则化方法与多尺度方法相结合,能够很好的抑制医学图像中的噪声和虚假边缘的干扰,这一方法能够在不采用任何附加拓扑控制的情况下自动控制轮廊曲线的拓扑结构变化,同时提取多个解剖结构,对来自不同成像技术的医学图像的分割,结果表明该方法是一种有效的医学图像分割方法。

References

[1]  Leventon M E, Grimson W E L, Faugeras O. Statistical shap influence in geodesicActive Contours. CPVR 2000, 1: 316-323
[2]  Gaselles V, Kimmel R, Sapiro G.Geodesic active contours. Int. J. Computer Vision, 1997, 22: 61-79
[3]  Caselles V, Catte F, Coll T. et al. A greometric model for active contours.Numerische Mathematik, 1993, 63: 1-31
[4]  Kichenassamy A, Kumar A, Olver P. et al. Gradient flows and geometric activecontour models. In IEEE Int′l Conf. Comp. Vision, 1995: 810-815
[5]  Malladi R, Sethian J A, Vemuri B C. Shape modeling with front propagation: a levelset approach. IEEE T. Patt. Anal. Mach. Intell., 1995, 17: 158-175
[6]  Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models: Int. J. ComputerVision, 1987, 1(1): 321-331
[7]  Siddiqi K, Lauziere Y B, Tannenbaum A. et al. Area and length minimizing flows forshape segmentation. IEEE T. Imag. Proc., 1998, 7: 433-443
[8]  Osher S, Sethian J A. Fronts propagating with curvature-dependent speed: Algorithmsbased on hamilton-jacobi formulation. J. Comp. Physics, 1988, 79: 12-49
[9]  Xu C, Prince J L. Snake, shape, and gradient vector flow. IEEE Trans. Pattern Anal.Machine Intell., 1998, 7(3): 359-369
[10]  Xu C, Prince J L. Generalized gradient vector flow external forces for activecontours. Signal Processing, 1998, 71: 131-139
[11]  Goldenberg R, Kimmel R, Rivlin E, et al. Fast Geodesic Active Contours. IEEETransactions on Image Processing, 2001, 10(10): 1467-1475
[12]  Paragios N, Deriche R. Geodesic active contours and level sets for the detectionand tracking of moving objects. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2000, 22: 266-280

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133