|
|
|
| Edge-preserving local fitting model for image segmentation |
| KONG Ding-ke1,2, WANG Guo-zhao1 |
1. Institute of Computer Graphics and Image Processing, Zhejiang University, Hangzhou 310027, China; 2. College of
Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou 310018, China |
|
|
|
Abstract Due to the fact that the segmentation accuracy of local binary fitting energy based variational model (LBF model) is highly dependent on kernel bandwidth, and it always leads to unsatisfactory segmentation results (e.g., unnecessary contours, rough boundaries) of inhomogeneous images because of inappropriate bandwidth, an novel edge-preserving local fitting model was proposed and well adapted to segment images with intensity inhomogeneity. First, a geodesic time based kernel using spatial location and spectral gradient was defined, and it provided an adaptive geodesic neighborhood for every pixel. Then, an efficient multichannel gradient based extension combined with adjusted dissimilarity measure was enforced to segment color and multispectral images. Experimental results showed that the proposed model can remain potential edge information while using larger bandwidth, and desirable segmentation results of both gray and color images can be obtained.
|
|
Published: 01 December 2010
|
|
|
用于图像分割的边界保持局部拟合模型
针对局部二值拟合变分水平集模型(LBF模型)的分割质量很大程度上取决于核带宽的选取,容易造成冗余轮廓、边界模糊等问题,提出一种基于边界保持局部拟合的变分水平集模型.该模型引入图像相依的测地时间定义核函数,结合空间距离和图像梯度,自适应地选取邻域采样点;同时,采用基于多波段的图像梯度,并相应地调整图像点的相异性测度,将模型的应用范围扩展至彩色及多光谱图像.实验结果表明：该模型能选取较大核带宽并有效保留潜在的边界信息,从而避免了核带宽的选取问题,较好地应用于灰度异质图像的精确分割;而且,该模型对彩色及多光谱图像的分割也同样有效.
|
|
| 1］ KASS M, WITKIN A, TERZOPOULOS D. Snakes: active contour models ［J］. International Journal of Computer Vision, 1988, 1(4): 322-331.
［2］ OSHER S, SETHIAN J A. Fronts propagating with curvaturedependent speed: algorithms based on HamiltonJacobi formulation ［J］. Journal of Computational Physics, 1988, 79(1): 12-49.
［3］ CASELLES V, KIMMER R, SAPIRO G. Geodesic active contours ［C］∥Proceedings 5th International Conference on Computer Vision. Boston: IEEE, 1995: 694-699.
［4］ MALLADI R, SETHIAN J A, VENMURI B C. Shape modeling with front propagation: a level set approach ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(2): 158-174.
［5］ CHAN T F, VESE L. Active contours without edges ［J］. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
［6］ CHEN L, ZHOU Y, WANG Y G, et al. GACV: geodesicaided CV method ［J］. Pattern Recognition, 2006, 39(7): 1391-1395.
［7］ LI C M, KAO C Y, GORE J C, et al. Implicit active contours driven by local binary fitting energy ［C］ ∥2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE,2007: 339-345.
［8］ LI C M, KAO C Y, GORE J C, et al. Minimization of regionscalable fitting energy for image segmentation ［J］. IEEE Transactions on Image Processing, 2008, 17(10): 1940-1949.
［9］ SOILLE P. Generalized geodesy via geodesic time ［J］. Pattern Recognition Letters, 1994, 15(12): 1235-1240.
［10］ SCHEUNDERS P. A multivalued image wavelet representation based on multiscale fundamental forms ［J］.IEEE Transactions on Image Processing, 2002, 11(5): 568-575.
［11］ MUMFORD D, SHAH J. Optimal approximation by piecewise smooth functions and associated variational problems ［J］. Communications on Pure Applied Math, 1989, 42(5): 577-685.
［12］ LI C M, XU C Y, GUI C, et al. Level set evolution without reinitialization: a new variational formulation ［C］∥2005 IEEE Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 430-436. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
