摘要
为了解决图像对象灰度分布不一致性的分割难题,提高图像分割速度,提出了一个全新的快速主动轮廓模型。它由曲线周围局部的统计信息驱动曲线发生形变演化,并使用图像中的边缘信息来引导曲线的演化方向。模型中,根据区域模板与演化曲线共同定义的局部统计信息创建数据拟合项,并应用水平集方法求解曲线的演化。对合成图像和医学图像的实验结果表明,本文提出的分割模型可以同时分割多个灰度不一致的对象,分割速度快,结果稳定,对噪声具有很好的鲁棒性。
In order to overcome the difficulties caused by intensities in-homogeneity and improve the speed of image segmentation,we propose a novel active contour model in which the curve evolution is driven by the statistical information around the curve,and the curve is forced to march toward the boundary under the alignment term.In our model,the data fitting term,which is constructed by the local information between the curve and mask,is incorporated into a variational level set formulation to be solved.Experiment results on the synthetic and medical images demonstrate that our new active contour model can segment multi-objects with intensity in-homogeneity at a faster convergency speed,and it is robust to noise.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2010年第1期140-143,共4页
Journal of Optoelectronics·Laser
基金
国家"863"高技术研究发展计划资助项目(2006AA02Z346)
广东省自然科学基金团队资助项目(6200171)
佛山市禅城区产学研资助项目(2008B1034)
关键词
图像分割
灰度不一致
水平集方法
主动轮廓模型
局部区域能量
image segmentation
intensity inhomogeneity
level set method
active contour model
localizing region energy
