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...

一种基于遗传算法的双T-Snake模型图像分割方法

DOI: 10.11834/jig.20050108

Keywords: Snake模型,双T-Snake模型,图像分割,遗传算法

Full-Text   Cite this paper   Add to My Lib

Abstract:

Snake的初衷是为了进行图像分割,但它对初始位置过于敏感,且不能处理拓扑结构改变的问题。初始位置的敏感性可以用遗传算法来克服,因为它是一种全局优化算法,且有良好的数值稳定性。为了更精确地进行图像分割,本文提出了一种基于遗传算法的双T―Snake模型图像分割方法,它将双T―Snake模型解作为遗传算法的搜索空间,这既继承了T―Snake模型的拓扑改变能力,又加快了遗传算法的收敛速度。由于它利用遗传算法的全局优化性能,克服了Snake轮廓局部极小化的缺陷,从而可得到对目标的更精确的分割。将其应用于左心室MRI图像的分割,取得了较好的效果。

References

[1]  周明 孙树栋.遗传算原理及应用[M].北京:国防工业出版社,1999.5-35.
[2]  McInerney T J. Topologically adaptable deformable models for medical image analysis [ D ]. Department of Computer Science,University of Tornoto. Canada, 1997.
[3]  Kass M, Witkin A, Terzopulos D. Snakes: Active contour models[ A ]. In: Proceedings of the First International Conference on Computer Vision[ C ], London, 1987:259 ~ 269.
[4]  Xu G, Segawa E, Tsuji S. Robust active contours with insensitive parmenters[ J ]. Pattern Recoginetion, 1994,27 (7): 879 ~ 884.
[5]  Cohen L D, Cohen I. Finite element methods for active contour models and balloons for 2-D and 3-D Images[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993,15 ( 11 ): 1131 ~1147.
[6]  McInerney T, Terzopoulos D. Toplogy adaptive deformable surfaces for medical image volume segmentation [ J ]. IEEE Transactions on Medical Image, 1999,18(10) :840 ~850.
[7]  Giraldi Gilson A, Strauss Edilberto, Oliveira Antonio A. A boundary extraction method based on dual-T-Snakes and dynamic programming[ A]. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition ( CVPR 2000 ) [ C ], Hilton Head, South Carolina, USA, 2000,1:1044 ~ 1049.
[8]  Leroy B, Herlin I, Cohen L D. Finite-element methods for active contour models [ A ]. In: 12th International Conference Analysis and Optimizatuion of Systems[C], Paris, France, 1996:58 ~65.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133