基于改进主动轮廓模型的图像分割算法  

Image Segmentation Algorithm Based on Improved Active Contour Model

作　　者：庞冬冬[1] 史健芳[1] 

机构地区：[1]太原理工大学信息工程学院,山西太原030024

出　　处：《电视技术》2013年第1期41-44,共4页Video Engineering

基　　金：山西省自然科学基金项目(2009011018-2)

摘　　要：针对C-V模型对灰度不均匀的图像分割效果不理想的情况,提出一种改进的C-V模型。该模型在C-V模型的基础上,引入非加权的邻域平均和局部窗口方差概念,加快并精确了C-V模型的演化效果,同时在C-V模型的能量函数中加入惩罚项,使得C-V模型在演化过程中无须重新初始化,进一步提高了分割速度。仿真实验结果表明改进的C-V模型较原模型对灰度不均匀图像分割具有较好的分割效果。Aiming at the problem of the ineffective segmentation results of the non-uniform gray images for CV model, an improved C-V model is presented. The model, which is on the basis of the C-V model, can accelerate and make an accurate C-V model evolution effects by introducing the concept of the non-weighted neighborhood averaging and the local window variance. Meanwhile, the penalty term is put in the C-V model energy function in order to avoid the re - initialization in the process of evolution of the C-V model and improve the segmentation speed. Simulation results show that the improved CV model has better segmentation effect than the original model in the non -uniform gray images.

关 键 词：图像分割 CHAN-VESE模型 邻域平均 局部方差 

分 类 号：TN911.7[电子电信—通信与信息系统]