引入秩逼近函数的群相似性活动轮廓模型  

Active Contour Model with Group Similarity by Integrating Rank Approaching Function

作　　者：魏金金 WEI Jinjin(College of Mathematics and Information Science,Henan Normal University,Xinxiang 453003,China)

机构地区：[1]河南师范大学数学与信息科学学院

出　　处：《新乡学院学报》2019年第9期13-16,共4页Journal of Xinxiang University

基　　金：河南省高等学校重点科研项目(19A510016)

摘　　要：为了稳健处理序列图像中相似形状目标的提取问题,将一个比核范数更近似的光滑逼近函数引入群相似性活动轮廓(active contours with group similarity,ACGS)能量泛函模型,给出了求解该模型的优化算法,进行了仿真实验。结果表明:与传统的C-V(Chan-Vese)模型和ACGS模型相比,该优化算法能很好地保持序列图像中演化曲线的形状相似性。In order to robustly deal with the extraction of similar shape objects in sequential images, an approximation function more approximate than the kernel norm is introduced into the energy functional model of group similarity active contours with group similarity(ACGS). The optimization algorithm for solving the model is given and the simulation experiments are carried out. The results show that the proposed method is effective and effective. Compared with the traditional C-V(Chan-Vese) model and ACGS model, this optimization algorithm can keep the shape similarity of evolutionary curves in sequence images.

关 键 词：活动轮廓模型 秩逼近函数 核范数 形状相似性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]