Generalized sparse MRF appearance models
Generalized sparse MRF appearance models
复制标题
DOI：
10.1016/j.imavis.2009.07.010
复制
发表时间：
2010-06-01
影响因子：
4.7
通讯作者：
Bischof, Horst
中科院分区：
文献类型：
--
作者：
Donner, Rene;Langs, Georg;Bischof, Horst
依赖于局部搜索范式的图像分割或配准方法（例如，活动外观模型，活动轮廓）需要初始化，以提供要分割或定位的对象的相当大的重叠或粗略定位。在本文中，我们提出了一种不需要初始化的方法，而是通过将定位任务表述为马尔可夫随机场（MRF）的解，以全局方式对解剖结构进行定位。在搜索过程中，稀疏MRF外观模型（SAMs）将地标的几何结构和局部外观特征的先验信息与目标图像中的一组候选点相关联。他们将对应概率编码为MRF，在目标图像中的搜索相当于求解MRF。生成的节点标签定义了建模对象（例如椎骨序列）到目标图像兴趣点的映射。局部外观信息由基于对称的兴趣点和基于梯度向量流（GVF）的局部描述符捕获。或者，可以使用任意兴趣点。在两个数据集上的实验结果显示了该方法对复杂医学数据的适用性。该方法不需要初始化，并在整个图像中找到查询结构的最合理匹配。它提供了精确、可靠和快速的结构定位。(C) 2009 Elsevier B.V.版权所有
Image segmentation or registration approaches that rely on a local search paradigm (e.g. Active Appearance Models, Active Contours) require an initialization that provides for considerable overlap or a coarse localization of the object to be segmented or localized. In this paper we propose an approach that does not need such an initialization, but localizes anatomical structures in a global manner by formulating the localization task as the solution of a Markov Random Field (MRF).During search Sparse MRF Appearance Models (SAMs) relate a priori information about the geometric configuration of landmarks and local appearance features to a set of candidate points in the target image. They encode the correspondence probabilities as an MRF, and the search in the target image is equivalent to solving the MRF. The resulting node labels define a mapping of the modeled object (e.g. a sequence of vertebrae) to the target image interest points. The local appearance information is captured by novel symmetry-based interest points and local descriptors derived from Gradient Vector Flow (GVF). Alternatively, arbitrary interest points can be used. Experimental results are reported for two data-sets showing the applicability to complex medical data. The approach does not require initialization and finds the most plausible match of the query structure in the entire image. It provides for precise, reliable and fast localization of the structure. (C) 2009 Elsevier B.V. All rights reserved.