Consistent landmark and intensity-based image registration

Two new consistent image registration algorithms are presented: one is based on matching corresponding landmarks and the other is based on matching both landmark and intensity information. The consistent landmark and intensity registration algorithm produces good correspondences between images near landmark locations by matching corresponding landmarks and away from landmark locations by matching the image intensities. In contrast to similar unidirectional algorithms, these new consistent algorithms jointly estimate the forward and reverse transformation between two images while minimizing the inverse consistency error-the error between the forward (reverse) transformation and the inverse of the the reverse (forward) transformation. This reduces the ambiguous correspondence between the forward and reverse transformations associated with large inverse consistency errors. In both algorithms a thin-plate spline (TPS) model is used to regularize the estimated transformations. Two-dimensional (2-D) examples are presented that show the inverse consistency error produced by the traditional unidirectional landmark TPS algorithm can be relatively large and that this error is minimized using the consistent landmark algorithm. Results using 2-D magnetic resonance imaging data are presented that demonstrate that using landmark and intensity information together produce better correspondence between medical images than using either landmarks or intensity information alone.     

稳健的图像匹配方法

景象匹配是计算机视觉研究的一个重要方向,如何在复杂的环境下提高匹配概率与定位精度是其亟待解决的难点之一。在分析畸变校正的量化噪声为高斯噪声的基础上,提出了基于特征和时空关联的积相关图像匹配算法。采用基于噪声抑制小波边缘检测方法,提取实时图和基准图的边缘特征;基于归一化积相关实现序列实时图(3帧)与基准图的匹配,再根据位置信息实现相关峰值的数据融合得到匹配点。此方法克服了因面积增大由几何失真导致的匹配概率下降的缺点,提高了匹配概率,具有较好的匹配稳健性。     

Accurate image registration for MAP image super-resolution

The accuracy of image registration plays a dominant role in image super-resolution methods and in the related literature, landmark-based registration methods have gained increasing acceptance in this framework. In this work, we take advantage of a maximum a posteriori (MAP) scheme for image super-resolution in conjunction with the maximization of mutual information to improve image registration for super-resolution imaging. Local as well as global motion in the low-resolution images is considered. The overall scheme consists of two steps. At first, the low-resolution images are registered by establishing correspondences between image features. The second step is to fine-tune the registration parameters along with the high-resolution image estimation, using the maximization of mutual information criterion. Quantitative and qualitative results are reported indicating the effectiveness of the proposed scheme, which is evaluated with different image features and MAP image super-resolution computation methods.     

Consistent image alignment for video mosaicing

Image mosaicing is widely used in computer vision applications. In this paper, a new globally consistent image alignment method for video mosaicing is presented. Due to various uncertainties on noise, illumination, and modeling, the problem of global image alignment is considered as a stochastic estimation problem. The augmented system state consists of the transformation parameters of video image sequences. The system motion model, the augmentation model, and the observation model are constructed. The homography parameters of image sequences are augmented and estimated recursively with augmented Kalman filter in a common state vector and covariance matrix. Some experimental results are provided to validate the performance of the proposed method. The proposed image alignment method can handle the uncertainty efficiently. Image alignment is globally consistent and accurate.     

Hybrid retinal image registration.

This work studies retinal image registration in the context of the National Institutes of Health (NIH) Early Treatment Diabetic Retinopathy Study (ETDRS) standard. The ETDRS imaging protocol specifies seven fields of each retina and presents three major challenges for the image registration task. First, small overlaps between adjacent fields lead to inadequate landmark points for feature-based methods. Second, the non-uniform contrast/intensity distributions due to imperfect data acquisition will deteriorate the performance of area-based techniques. Third, high-resolution images contain large homogeneous nonvascular/texureless regions that weaken the capabilities of both feature-based and area-based techniques. In this work, we propose a hybrid retinal image registration approach for ETDRS images that effectively combines both area-based and feature-based methods. Four major steps are involved. First, the vascular tree is extracted by using an efficient local entropy-based thresholding technique. Next, zeroth-order translation is estimated by maximizing mutual information based on the binary image pair (area-based). Then image quality assessment regarding the ETDRS field definition is performed based on the translation model. If the image pair is accepted, higher-order transformations will be involved. Specifically, we use two types of features, landmark points and sampling points, for affine/quadratic model estimation. Three empirical conditions are derived experimentally to control the algorithm progress, so that we can achieve the lowest registration error and the highest success rate. Simulation results on 504 pairs of ETDRS images show the effectiveness and robustness of the proposed algorithm.     

图像配准技术研究进展

图像配准是解决图像融合、图像镶嵌和变化检测等问题的必要前提,其应用遍及军事、遥感、医学和计算机视觉等多个领域.简要回顾了图像配准技术的发展史和研究现状,重点阐述了当前的技术热点和应用趋势,最后展望了进一步的研究方向.     

Fast parametric elastic image registration

We present an algorithm for fast elastic multidimensional intensity-based image registration with a parametric model of the deformation. It is fully automatic in its default mode of operation. In the case of hard real-world problems, it is capable of accepting expert hints in the form of soft landmark constraints. Much fewer landmarks are needed and the results are far superior compared to pure landmark registration. Particular attention has been paid to the factors influencing the speed of this algorithm. The B-spline deformation model is shown to be computationally more efficient than other alternatives. The algorithm has been successfully used for several two-dimensional (2-D) and three-dimensional (3-D) registration tasks in the medical domain, involving MRI, SPECT, CT, and ultrasound image modalities. We also present experiments in a controlled environment, permitting an exact evaluation of the registration accuracy. Test deformations are generated automatically using a random hierarchical fractional wavelet-based generator.     

Performance bounds on image registration

Registration is a fundamental step in image processing systems where there is a need to match two or more images. Applications include motion detection, target recognition, video processing, and medical imaging. Although a vast number of publications have appeared on image registration, performance analysis is usually performed visually, and little attention has been given to statistical performance bounds. Such bounds can be useful in evaluating image registration techniques, determining parameter regions where accurate registration is possible, and choosing features to be used for the registration. In this paper, Crame/spl acute/r-Rao bounds on a wide variety of geometric deformation models, including translation, rotation, shearing, rigid, more general affine and nonlinear transformations, are derived. For some of the cases, closed-form expressions are given for the maximum-likelihood (ML) estimates, as well as their variances, as space permits. The bounds are also extended to unknown original objects. Numerical examples illustrating the analytical performance bounds are presented.     

Incremental variations of image moments for nonlinear image registration

In this paper, we use image moments to solve the problem of estimating deformation fields given a pair of images as input. We use a single family of polynomials to parameterize the deformation field and to define image moments. In this way, variations in image moments can be represented by a set of linear equations. We solve these equations iteratively for the deformation parameters between two shapes. Our approach improves existing moment-based registration methods in both robustness to noise and convergence rate. In addition, our method does not rely on solving the correspondence problem. We have extensively tested our new method on both synthetically deformed MPEG-7 shapes and real-world biomedical images.     

医学图像配准中的数据抽样方法研究

针对在基于灰度的医学图像配准中,传统数据抽样方法在过抽样时产生较多的局部极值点问题,提出了基于浮动图像灰度概率分布和其梯度信息的抽样方法.通过对人体脑部的刚体配准实验,从函数曲线和收敛性能方面,对比分析了五种数据抽样方法.实验结果表明,新抽样方法可以有效地减少局部极值点,提高归一化互信息测度的收敛性能.     

基于灰度的医学图像配准技术研究

医学图像配准是医学图像处理的一项重要技术,广泛应用于临床诊断和治疗、计划设计、外科手术等领域中.从基于灰度的医学图像配准角度,描述了医学图像配准的基本过程和优化策略,着重阐述了目前普遍采用的相关技术和方法的表示形式,以及这些方法的特点和应用领域,并进一步分析了在这一方面的研究中存在的问题和未来的发展方向.     

Likelihood maximization approach to image registration

A likelihood maximization approach to image registration is developed in this paper. It is assumed that the voxel values in two images in registration are probabilistically related. The principle of maximum likelihood is then exploited to find the optimal registration: the likelihood that given image f, one has image g and given image g, one has image f is optimized with respect to registration parameters. All voxel pairs in the overlapping volume or a portion of it can be used to compute the likelihood. A knowledge-based method and a self-consistent technique are proposed to obtain the probability relation. In the knowledge-based method, prior knowledge of the distribution of voxel pairs in two registered images is assumed, while such knowledge is not required in the self-consistent method. The accuracy and robustness of the likelihood maximization approach is validated by single modality registration of single photon emission computed tomographic (SPECT) images and magnetic resonance (MR) images and by multimodality registration (MR/SPECT). The results demonstrate that the performance of the likelihood maximization approach is comparable to that of the mutual information maximization technique. Finally the relationship between the likelihood approach and the entropy, conditional entropy, and mutual information approaches is discussed.     

Medical image registration using mutual information

Analysis of multispectral or multitemporal images requires proper geometric alignment of the images to compare corresponding regions in each image volume. Retrospective three-dimensional alignment or registration of multimodal medical images based on features intrinsic to the image data itself is complicated by their different photometric properties, by the complexity of the anatomical objects in the scene and by the large variety of clinical applications in which registration is involved. While the accuracy of registration approaches based on matching of anatomical landmarks or object surfaces suffers from segmentation errors, voxel-based approaches consider all voxels in the image without the need for segmentation. The recent introduction of the criterion of maximization of mutual information, a basic concept from information theory, has proven to be a breakthrough in the field. While solutions for intrapatient affine registration based on this concept are already commercially available, current research in the field focuses on interpatient nonrigid matching.     

F-information measures in medical image registration

A measure for registration of medical images that currently draws much attention is mutual information. The measure originates from information theory, but has been shown to be successful for image registration as well. Information theory, however, offers many more measures that may be suitable for image registration. These all measure the divergence of the joint distribution of the images' grey values from the joint distribution that would have been found had the images been completely independent. This paper compares the performance of mutual information as a registration measure with that of other F-information measures. The measures are applied to rigid registration of positron emission tomography (PET)/magnetic resonance (MR) and MR/computed tomography (CT) images, for 35 and 41 image pairs, respectively. An accurate gold standard transformation is available for the images, based on implanted markers. The registration performance, robustness and accuracy of the measures are studied. Some of the measures are shown to perform poorly on all aspects. The majority of measures produces results similar to those of mutual information. An important finding, however, is that several measures, although slightly more difficult to optimize, can potentially yield significantly more accurate results than mutual information.     

Fundamental performance limits in image registration

The task of image registration is fundamental in image processing. It often is a critical preprocessing step to many modern image processing and computer vision tasks, and many algorithms and techniques have been proposed to address the registration problem. Often, the performances of these techniques have been presented using a variety of relative measures comparing different estimators, leaving open the critical question of overall optimality. In this paper, we present the fundamental performance limits for the problem of image registration as derived from the Cramer-Rao inequality. We compare the experimental performance of several popular methods with respect to this performance bound, and explain the fundamental tradeoff between variance and bias inherent to the problem of image registration. In particular, we derive and explore the bias of the popular gradient-based estimator showing how widely used multiscale methods for improving performance can be explained with this bias expression. Finally, we present experimental simulations showing the general rule-of-thumb performance limits for gradient-based image registration techniques.     

Bayesian technique for image classifying registration

In this paper, we address a complex image registration issue arising while the dependencies between intensities of images to be registered are not spatially homogeneous. Such a situation is frequently encountered in medical imaging when a pathology present in one of the images modifies locally intensity dependencies observed on normal tissues. Usual image registration models, which are based on a single global intensity similarity criterion, fail to register such images, as they are blind to local deviations of intensity dependencies. Such a limitation is also encountered in contrast-enhanced images where there exist multiple pixel classes having different properties of contrast agent absorption. In this paper, we propose a new model in which the similarity criterion is adapted locally to images by classification of image intensity dependencies. Defined in a Bayesian framework, the similarity criterion is a mixture of probability distributions describing dependencies on two classes. The model also includes a class map which locates pixels of the two classes and weighs the two mixture components. The registration problem is formulated both as an energy minimization problem and as a maximum a posteriori estimation problem. It is solved using a gradient descent algorithm. In the problem formulation and resolution, the image deformation and the class map are estimated simultaneously, leading to an original combination of registration and classification that we call image classifying registration. Whenever sufficient information about class location is available in applications, the registration can also be performed on its own by fixing a given class map. Finally, we illustrate the interest of our model on two real applications from medical imaging: template-based segmentation of contrast-enhanced images and lesion detection in mammograms. We also conduct an evaluation of our model on simulated medical data and show its ability to take into account spatial variations of intensity dependencies while keeping a good registration accuracy.     

Volume image registration by cross-entropy optimization

Cross-entropy (CE), an information-theoretic measure, quantifies the difference between two probability density functions. This measure is applied to volume image registration. When a good prior estimation of the joint distribution of the voxel values of two images in registration is available, the CE can be minimized to find an optimal registration. If such a prior estimation is not available, one seeks the registration which gives a joint distribution different from unlikely ones as much as possible, i.e., the CE is maximized to find an optimal registration. When the unlikely distribution is a uniform one, CE maximization reduces to joint entropy minimization; when the unlikely distribution is proportional to one of the marginal distributions, it reduces to conditional entropy minimization; when the unlikely distribution is the product of two marginal distributions, it degenerates to mutual-information maximization. These different CEs are added together and are used as criteria for image registration. The accuracy and robustness of this new approach are tested and compared using a likely joint distribution and various unlikely joint distributions and their combinations.     

改进PSO算法在图像配准中的应用

图像配准是目前图像处理中的热点,很大程度上因为它是图像融合的前提,具有重要的研究价值.粒子群算法是一种基于群体搜索策略的自适应随机算法,由于该算法实现简单、参数较少等特点被广泛使用.针对标准PSO易陷于局部最优的问题,对标准PSO进行了改进.实验过程中,参考图像和浮动图像的相似性测度采用的是峰值信噪比(PSNR).通过实验结果对比,改进后的算法由于克服了容易陷入局部最优解的问题从而提高了配准精度.     

结合图像信息熵和特征点的图像配准方法

在分析当前主要的图像配准技术之后,针对图像特征点的分布和同名点的匹配问题,提出了结合图像信息熵和特征点的图像配准方法。首先对图像进行一定程度的分块,根据信息论的方法,计算每一块的信息熵,信息熵的大小基本反映了各个模块的纹理变换情况。然后根据各个模块的信息熵大小,进行图像的粗匹配。之后在各个模块提取出一定数目的特征点,信息熵大,纹理信息丰富,选取的特征点就相应较多,反之则纹理信息变化不大,选取的特征点数目较少。最后根据这些具有代表性的同名点进行精确匹配。为验证该方法的有效性,对两幅图像进行传统方法和改进的图像配准方法的比较。     

Adaptive image registration via hierarchical Voronoi subdivision

Advances in image acquisition systems have made it possible to capture high-resolution images of a scene, recording considerable scene details. With increased resolution comes increased image size and geometric difference between multiview images, complicating image registration. Through Voronoi subdivision, we subdivide large images into small corresponding regions, and by registering small regions, we register the images in a piecewise manner. Image subdivision reduces the geometric difference between regions that are registered and simplifies the correspondence process. The proposed method is a hierarchical one. While previous methods use the same block size and shape at a hierarchy, the proposed method adapts the block size and shape to the local image details and geometric difference between the images. This adaptation makes it possible to keep geometric difference between corresponding regions small and simplifies the correspondence process. Implementational details of the proposed image registration method are provided, and experimental results on various types of images are presented and analyzed.