基于凸优化的自适应CV模型  

Adaptive CV model using convex optimization

作　　者：朱晓舒[1,2] 孙权森[1] 夏德深[1] 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094 [2]南京师范大学分析测试中心,南京210097

出　　处：《计算机应用研究》2012年第2期779-781,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(60773172);国家教育部博士学科点基金资助项目(200802880017);江苏省自然科学基金资助项目(BK2008411)

摘　　要：针对CV模型分割精度不高、分割速度缓慢和易陷于局部最优等缺点,提出了一种新的基于凸优化的自适应CV模型。首先,引入了自适应权重项,对拟合中心的计算采用加权平均,提高了拟合中心计算的准确性;然后,在模型中加入了凸优化技术,以获取模型的全局最优解;最后,采用了Split Bregman方法进行快速求解,有效地提高了分割效率。实验结果表明,基于凸优化的自适应CV模型有效地提高了分割精度和效率,对初始化也具有较好的鲁棒性。The CV model can not accurately segment an image,and the segmentation speed is slow,and the model is very easy to trapp in local optimum.In order to solve the problems,this paper proposed a new adaptive CV model using convex optimization.First,to improve the accuracy of fitting center,it introduced the adaptive weight and used the weighted average to caculate the fitting center.Second,convex optimization was added to the new model to get global minima.Finally,the Split Bregman method could effectively improve the segmentation speed.Experimental results demonstrate that the proposed algorithm can get the more accurate and efficient segmentation results,and it is robust to the choice of initialization.

关 键 词：图像分割 CV模型 凸优化 SplitBregman 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]