【信息技术】【2011.11】离散图像配准：一种混合模式

本文为法国巴黎中央理工学院（作者：Aristeidis SOTIRAS）的博士论文，共182页。

本文主要研究离散方法在稠密变形图像配准/融合中的应用。本文的主要贡献是提出了一种基于图形技术的图像/几何信息耦合的原理性配准框架。这种公式是从成对MRF的观点推导出来的，将一致性强加于各自的解决方案，它同时解决了两个问题。该框架用于处理成对图像融合（提出了对称和非对称变量）以及种群建模中的分组配准。该框架的主要特点在于计算效率和通用性。该公式的离散性使得框架在图标相似性度量以及地标提取和关联技术方面具有模块化的特点。在光流估计和三维医学数据中使用标准基准数据库的结果显示了我们所提出方法的潜力。

This thesis is devoted to dense deformable imageregistration/fusion using discrete methods. The main contribution of the thesisis a principled registration framework coupling iconic/geometric informationthrough graph-based techniques. Such a formulation is derived from a pair-wiseMRF view-point and solves both problems simultaneously while imposingconsistency on their respective solutions. The proposed framework was used tocope with pair-wise image fusion (symmetric and asymmetric variants areproposed) as well as group-wise registration for population modeling. The mainqualities of our framework lie in its computational efficiency and versatility.The discrete nature of the formulation renders the framework modular in termsof iconic similarity measures as well as landmark extraction and associationtechniques. Promising results using a standard benchmark database in opticalflow estimation and 3D medical data demonstrate the potentials of our methods.

1. 引言
2. 变形配准综述
3. 混合配准
4. 对称混合配准
5. 群组配准
6. 结论

更多精彩文章请关注公众号：