Liu Chengyin, Ma Jiayi, Ma Yong, Huang Jun
J Opt Soc Am A Opt Image Sci Vis. 2016 Jul 1;33(7):1267-76. doi: 10.1364/JOSAA.33.001267.
Registration of retinal images taken at different times, from different perspectives, or with different modalities is a critical prerequisite for the diagnoses and treatments of various eye diseases. This problem can be formulated as registration of two sets of sparse feature points extracted from the given images, and it is typically solved by first creating a set of putative correspondences and then removing the false matches as well as estimating the spatial transformation between the image pairs or solved by estimating the correspondence and transformation jointly involving an iteration process. However, the former strategy suffers from missing true correspondences, and the latter strategy does not make full use of local appearance information, which may be problematic for low-quality retinal images due to a lack of reliable features. In this paper, we propose a feature-guided Gaussian mixture model (GMM) to address these issues. We formulate point registration as the estimation of a feature-guided mixture of densities: A GMM is fitted to one point set, such that both the centers and local features of the Gaussian densities are constrained to coincide with the other point set. The problem is solved under a unified maximum-likelihood framework together with an iterative expectation-maximization algorithm initialized by the confident feature correspondences, where the image transformation is modeled by an affine function. Extensive experiments on various retinal images show the robustness of our approach, which consistently outperforms other state-of-the-art methods, especially when the data is badly degraded.
对在不同时间、从不同视角或使用不同模态拍摄的视网膜图像进行配准，是各种眼科疾病诊断和治疗的关键前提。这个问题可以被表述为对从给定图像中提取的两组稀疏特征点进行配准，通常的解决方法是先创建一组假定的对应关系，然后去除错误匹配，并估计图像对之间的空间变换，或者通过联合估计对应关系和变换（涉及一个迭代过程）来解决。然而，前一种策略存在遗漏真实对应关系的问题，而后一种策略没有充分利用局部外观信息，这对于由于缺乏可靠特征而质量较低的视网膜图像可能会有问题。在本文中，我们提出了一种特征引导的高斯混合模型（GMM）来解决这些问题。我们将点配准表述为对特征引导的密度混合的估计：将一个高斯混合模型拟合到一个点集上，使得高斯密度的中心和局部特征都被约束为与另一个点集一致。该问题在一个统一的最大似然框架下，通过由可靠特征对应关系初始化的迭代期望最大化算法来解决，其中图像变换由仿射函数建模。在各种视网膜图像上进行的大量实验表明了我们方法的鲁棒性，该方法始终优于其他先进方法, 特别是在数据严重退化的情况下。
