计算机科学 ›› 2016, Vol. 43 ›› Issue (Z11): 193-196.doi: 10.11896/j.issn.1002-137X.2016.11A.043
张辉,朱家明,陈静,吴杰
ZHANG Hui, ZHU Jia-ming, CHEN Jing and WU Jie
摘要： 由于医学图像中的复杂目标通常难以被完全分割,提出标记分水岭与改进型Li模型的组合图像分割算法。改进型Li模型构造了符号压力函数来取代传统的停止函数,解决了曲线单向演化的问题。标记分水岭具有较强的抑制噪声的能力,对医学图像的弱边缘具有较强的捕获能力。所以首先运用标记分水岭算法对图像进行预分割,快速准确定位目标区域边缘信息。再引入改进型Li模型算法,通过符号压力函数来指引曲线演化方向,控制演化速度大小,实现对复杂目标的完全分割。实验结果表明:全局信息和边缘信息都能被获得,该组合算法对医学图像中的复杂目标的分割效果较满意。
| [1] 江贵平,秦文健,周寿军,等.医学图像分割及其发展现状[J].计算机学报,2015,8(6):1222-1241 [2] 刁智华,赵春江,郭新宇,等.分水岭算法的改进方法研究[J].计算机工程,2010,6(17):4-6 [3] Osher S,Sethian J A.Fronts propagating with curvature dependent speed:Algorithms based on the Hamilton-Jacobi formulation [J].Journal of Computational Physics,1998,79:12-49 [4] Li C M,Kao C Y,Gore J C,et al.Minimization of region-scalable fitting energy for image segmentation [J].IEEE Trans on pattern Analysis and Machine Intelligence,2008,7(10):1940-1949 [5] Li C,Xu C,Gui C,et al.Level set evolution without re-initialization:A new variational formulation[C]∥IEEE Conference on Computer Vision and Patten Recognition(CVPR).2005:430-436 [6] Vincent L,Soilh P.Watersheds in digital space:An efficient algorithm based on immersion simulations [J].IEEE Translations on Pattern Analysis and Machine Interpretation,1991,13(6):583-598 [7] 阮秋琦,阮宇智,等.数字图像处理[M].北京:电子工业出版社,2011:497-502 [8] 赵珊,王水.结合进化规划的图像分水岭分割技术[J].计算机科学,2011,38(5):265-267 [9] 方江雄.变分和偏微分方法在图像分割中的应用[M].北京:中国石化出版社,2015:20-23 [10] Xu C Y,Yezzi A,Prince J L.On the relationship between parametric and geometric active contour[C]∥Processing of 34th Asilomar Conference on Signals Systems and Computer.Pacific Grove:IEEE Press,2000:483-489 [11] Salah M B,Mitiche A,Ayed I B.Multiregion image segmentation by parametric kernel graph cuts[J].IEEE Transactions on Image Processing,2011,20(2),545-557 [12] Han X Z,Jian Z.A nonlinear image enhancement algorithmbased on partial differential equations[C]∥IEEE 10th International Conference Signal Processing.2010:1114-1116 |
| No related articles found! |
|
||
首页