基于核函数的活动轮廓模型 - 计算机辅助设计与图形学学报.pdf

第27 卷 第3 期 计算机辅助设计与图形学学报 Vol. 27 No.3 2015 年3 月 Journal of Computer-Aided Design Computer Graphics Mar. 2015 基于核函数的活动轮廓模型 1,2) 1) 1) 1) 朱晓舒 , 孙权森 , 夏德深 , 孙怀江 1) (南京理工大学计算机科学与工程学院 南京 210094) 2) (南京师范大学分析测试中心 南京 210046) (xiaoshu_zhu78@163.com) 摘 要: 为了改善活动轮廓模型的分割精度和效率, 提出一种基于核函数的活动轮廓模型. 该模型采用鲁棒的非欧 氏距离度量构造能量泛函, 提高了模型的分割精度; 使用指数类型的核特征函数来提升收敛速度; 最后在模型中还 加入了水平集正则项, 以避免水平集的重新初始化. 实验结果表明, 文中模型在分割精度和分割效率上都要强于 Chan-Vese 模型. 关键词：图像分割; Chan-Vese 模型; 水平集方法; 核特征函数 中图法分类号：TP391.41 Active Contours Driven by Kernel-Based Fitting Energy Zhu Xiaoshu1,2), Sun Quansen1), Xia Deshen1), and Sun Huaijiang1) 1) (School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094) 2) (Center for Analysis and Testing, Nanjing Normal University, Nanjing 210046) Abstract: In this paper, a new region-based active contour model using kernel-based fitting energy is proposed to improve the accuracy and efficiency of segmentation. The proposed kernel-based fitting energy is defined as a kernel function inducing a robust non-Euclidean distance measurement to segment images more effectively. In addition, an exponential-type kernel-based function in our model is used, which leads to faster converge. At last, to avoid costly computation of re-initialization widely adopted in traditional level set methods, we introduce a new penalty energy as a regularization term. Experimental results demonstrate that our model can segment images more precisely and much faster than the well-known Chan-Vese model. Key words: image segmentation; Chan-Vese model; level set method; kernel-based function 图像分割在计算机视觉中起着重要的作用, 曲线的表达形式不同,