Dense image registration through MRFs and efficient linear programming
Dense image registration through MRFs and efficient linear programming
复制标题
DOI：
10.1016/j.media.2008.03.006
复制
发表时间：
2008-12-01
影响因子：
10.9
通讯作者：
Paragios, Nikos
中科院分区：
文献类型：
--
作者：
Glocker, Ben;Komodakis, Nikos;Paragios, Nikos
在本文中，我们介绍了一种新颖而有效的密集图像配准方法，该方法不需要所采用的代价函数的导数。在这种情况下，使用离散马尔可夫随机场目标函数来表示配准问题。首先，对于变量的降维，我们假设密集的变形场可以用少量的控制点(配准网格)和内插策略来表示。然后，使用投影在控制点上的图像成本的离散和(使用任意相似性度量)和根据网格上的邻域系统惩罚变形场上的局部偏差的平滑项来表示配准成本。对于离散方法，搜索空间被量化，从而得到完全离散的模型。为了考虑大变形并在高分辨率水平上产生结果，考虑了一种迭代更新最优解的多尺度增量方法。这是通过源图像向目标图像的连续变形来完成的。使用原始对偶原理的有效线性规划被认为是恢复成本函数的最小势能。使用已知变形的合成数据和实际数据的非常有希望的结果证明了我们方法的潜力。(C)2008爱思唯尔B.V.保留所有权利。
In this paper, we introduce a novel and efficient approach to dense image registration, which does not require a derivative of the employed cost function. In such a context, the registration problem is formulated using a discrete Markov random field objective function. First, towards dimensionality reduction on the variables we assume that the dense deformation field can be expressed using a small number of control points (registration grid) and an interpolation strategy. Then, the registration cost is expressed using a discrete sum over image costs (using an arbitrary similarity measure) projected on the control points, and a smoothness term that penalizes local deviations on the deformation field according to a neighborhood system on the grid. Towards a discrete approach, the search space is quantized resulting in a fully discrete model. In order to account for large deformations and produce results on a high resolution level, a multi-scale incremental approach is considered where the optimal solution is iteratively updated. This is done through successive morphings of the source towards the target image. Efficient linear programming using the primal dual principles is considered to recover the lowest potential of the cost function. Very promising results using synthetic data with known deformations and real data demonstrate the potentials of our approach. (C) 2008 Elsevier B.V. All rights reserved.