隐含先验约束MRF模型的目标形状分割方法  

MRF model with implicit shape prior for object shape segmentation

作　　者：孙建中[1,2] 熊忠阳[1] 张玉芳[1] 

机构地区：[1]重庆大学计算机学院,重庆400030 [2]商丘师范学院计算机学院,河南商丘476000

出　　处：《计算机工程与设计》2014年第1期208-212,共5页Computer Engineering and Design

基　　金：中央高校基本科研业务费基金项目(CDJXS10180004);重庆市自然科学基金项目(CSTC2008BB2191)

摘　　要：在形状变化、被遮挡、噪声情况下,存在难以完整分割目标形状的问题。提出一种采用隐含形状约束马尔可夫随机场模型的轮廓分割方法。引入目标的先验形状知识,用水平集符号距离函数隐含表示目标的先验形状模型,以先验形状模型作为约束构造出MRF能量函数;采用graph cut法求解能量函数极小值,利用形状对准和最大流法演化初始轮廓,快速准确地分割出目标的形状。实验结果表明,新方法能有效快速分割带遮挡、噪声以及发生形状变化的目标,增强了形状分割的鲁棒性。To deal with shape segmentation of the object in complicated scenes, a novel method based on MRF model with implicit shape prior is proposed. An implicit shape model with level set signed distance function is built to improve the accuracy of object segmentation, and a MRF energy function with the constraint of the existing shape prior is constructed. The optimal value of energy function is found by graph cut algorithm. The precise segmentation of object is obtained by applying the shape align ment and max-flow method to evolve the initial contour. Experimental results show that the proposed method can better cope with the clutter and noise, as well as partial occlusions and affine transformation of the shape, thus the robust stability of seg mentation result is improved.

关 键 词：马尔可夫随机场 先验形状 水平集 图割算法 活动轮廓 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]