Narrow Results

This paper addresses the functional localization of intra-patient images of the brain. Functional images of the brain (fMRI and PET) provide information about brain function and metabolism whereas anatomical images (MRI and CT) supply the localization of structures with high spatial resolution. The goal is to find the geometric correspondence between functional and anatomical images in order to complement and fuse the information provided by each imaging modality. The proposed approach is based on a variational formulation of the image registration problem in the frequency domain. It has been implemented as a C/C$++$ library which is invoked from a GUI. This interface is routinely used in the clinical setting by physicians for research purposes (Inscanner, Alicante, Spain), and may be used as well for diagnosis and surgical planning. The registration of anatomic and functional intra-patient images of the brain makes it possible to obtain a geometric correspondence which allows for the localization of the functional processes that occur in the brain. Through 18 clinical experiments, it has been demonstrated how the proposed approach outperforms popular state-of-the-art registration methods in terms of efficiency, information theory-based measures (such as mutual information) and actual registration error (distance in space of corresponding landmarks).

A novel method to obtain point correspondence in pairs of images is presented. Our approach is based on automatically establishing correspondence between linear structures which appear in images using robust features such as orientation, width and curvature extracted from those structures. The extracted points can be used to register sets of images. The potential of the developed approach is demonstrated on mammographic images.

This paper proposes a hybrid approach to image registration for inferring the affine transformation that best matches a pair of partially overlapping aerial images. The image registration is formulated as a two-stage hybrid approach combining both phase correlation method (PCME) and optical flow equation (OFE) based estimation algorithm in a coarse-to-fine manner. With PCME applied at the highest level of decomposition, the initial affine parameter model could be first estimated. Subsequently, the OFE-based estimation algorithm is incorporated into the proposed hybrid approach using a multi-resolution mechanism. PCME is characterized by its insensitivity to large geometric transform between images, which can effectively guide the OFE-based registration. For image pairs under salient brightness variations, we propose a nonlinear image representation that emphasizes common intensity information, suppresses the non-common information between an image pair, and is suitable for the proposed coarse-to-fine hierarchical iterative processing. Experimental results demonstrate the accuracy and efficiency of our proposed approach using different types of aerial images.

Localizing facial features is a critical component in many computer vision applications such as expression recognition, face recognition, face tracking, animation, and red-eye correction. Practical applications require detectors that operate reliably under a wide range of conditions, including variations in illumination, pose, ethnicity, gender and age. One challenge for the development of such detectors is the inherent trade-off between robustness and precision. Robust detectors tend to provide poor localization and detectors sensitive to small changes in local structure, which are needed for precise localization, generate a large number of false alarms. Here we present an approach to this trade-off based on context dependent inference. First, robust detectors are used to detect contexts in which target features occur, then precise detectors are trained to localize the features given the detected context. This paper describes the approach and presents a thorough empirical examination of the parameters needed to achieve practical levels of performance, including the size of the training database, size of the detector's receptive fields and methods for information integration. The approach operates in real time and achieves, to our knowledge, the most accurate localization performance to date.

Scale invariant feature transform (SIFT) has been widely used in image matching. But when SIFT is introduced in the registration of remote sensing images, the keypoint pairs which are expected to be matched are often assigned two different value of main orientation owing to the significant difference in the image intensity between remote sensing image pairs, and therefore a lot of incorrect matches of keypoints will appear. This paper presents a method using rotation-invariant distance instead of Euclid distance to match the scale invariant feature vectors associated with the keypoints. In the proposed method, the feature vectors are reorganized into feature matrices, and fast Fourier transform (FFT) is introduced to compute the rotation-invariant distance between the matrices. Much more correct matches are obtained by the proposed method since the rotation-invariant distance is independent of the main orientation of the keypoints. Experimental results indicate that the proposed method improves the match performance compared to other state-of-art methods in terms of correct match rate and aligning accuracy.

Automatic retinal image registration is still a great challenge in computer aided diagnosis and screening system. In this paper, a new retinal image registration method is proposed based on the combination of blood vessel segmentation and scale invariant feature transform (SIFT) feature. The algorithm includes two stages: retinal image segmentation and registration. In the segmentation stage, the blood vessel is segmented by using the guided filter to enhance the vessel structure and the bottom-hat transformation to extract blood vessel. In the registration stage, the SIFT algorithm is adopted to detect the feature of vessel segmentation image, complemented by using a random sample consensus (RANSAC) algorithm to eliminate incorrect matches. We evaluate our method from both segmentation and registration aspects. For segmentation evaluation, we test our method on DRIVE database, which provides manually labeled images from two specialists. The experimental results show that our method achieves 0.9562 in accuracy (Acc), which presents competitive performance compare to other existing segmentation methods. For registration evaluation, we test our method on STARE database, and the experimental results demonstrate the superior performance of the proposed method, which makes the algorithm a suitable tool for automated retinal image analysis.

General machine vision algorithms are difficult to detect LCD sub-pixel level defects. By studying the LCD screen images, we found that the pixels in the LCD screen are regularly arranged. The spectrum distribution of LCD images, which is obtained by the Fourier transform, is relatively consistent. According to this feature, a method of sub-pixel defect detection based on notch filter and image registration is proposed. First, we take a defect-free template image to establish registration template and notch-filtering template; then we take the defect images for image registration with registration template, and solve the offset problem. After the notch-filter template filtering the background texture, the defect is more obvious; Finally the defects are obtained by the threshold segmentation method. The experiment results show that the proposed method can detect sub-pixel defects accurately and quickly.

Occlusion detection is an important problem in 3D computer vision which uses multiple views, such as stereo vision. The presence of occlusion complicates the problem of vergence and the subsequent stereo matching in the generation of 3D data. This paper presents an approach which detects the presence of occlusion concurrently during the vergence process. The main limitation of the approach where the maximum correlation coefficient can be very high even when a significant amount of occlusions is present in the stereo images is shown. This paper presents an adaptive method of adjusting the correlation threshold with respect to the contrast-levels of the image being analyzed to alleviate this limitation. The proposed adaptive threshold method ensures that the sensitivity of detecting mismatches is less dependent upon the contrast-levels of the image being analyzed. The computational advantage of the proposed adaptive threshold method over the fixed threshold method is also presented. Experimental results which show the strengths of the proposed adaptive threshold method over the fixed threshold method on real scenes are given.

Graphics processing unit (GPU) has surfaced as a high-quality platform for computer vision-related systems. In this paper, we propose a straightforward system consisting of a registration and a fusion method over GPU, which generates good results at high speed, compared to non-GPU-based systems. Our GPU-accelerated system utilizes existing methods through converting the methods into the GPU-based platform. The registration method uses point correspondences to find a registering transformation estimated with the incremental parameters in a coarse-to-fine way, while the fusion algorithm uses multi-scale methods to fuse the results from the registration stage. We evaluate performance with the same methods that are executed over both CPU-only and GPU-mounted environment. The experiment results present convincing evidences of the efficiency of our system, which is tested on a few pairs of aerial images taken by electro-optical and infrared sensors to provide visual information of a scene for environmental observatories.

This paper presents a technique for face recognition that is based on image registration. The face recognition technique consists of three parts: a training part, an image registration part and a post-processing part. The image registration technique is based on finding a set of feature points in the two images and using these feature points for registration. This is done in four steps. In the first, images are filtered with the Mexican-hat wavelet to obtain the feature point locations. In the second, the Zernike moments of neighborhoods around the feature points are calculated and compared in the third step to establish correspondence between feature points in the two images. In the fourth, the transformation parameters between images are obtained using an iterative least squares technique to eliminate outliers.^1,2 During training, a set of images are chosen as the training images and the Zernike moments for the feature points of the training images are obtained and stored. The choice of training images depends on the changes of poses and illumination that are expected. In the registration part, the transformation parameters to register the training images with the images under consideration are obtained. In the post-processing, these transformation parameters are used to determine whether a valid match is found or not.

The performance of the proposed method is evaluated using various face databases^3–5 and it is compared with the performance of existing techniques. Results indicate that the proposed technique gives excellent results for face recognition in conditions of varying pose, illumination, background and scale.

Image registration of multimodal remote sensing images plays a vital role in remote sensing image analysis. However, there are significant nonlinear intensity differences between multimodal remote sensing image pairs, making it difficult for most traditional image registration algorithms to meet the registration requirements. In this paper, we propose a novel edge descriptor utilizing edge information, which has not only affine invariance but is also insensitive to nonlinear intensity differences. Moreover, we utilize the proposed descriptor to design a multimodal image registration algorithm. We use several different multimodal image pairs to evaluate the proposed algorithm. The experimental results show that the proposed algorithm holds a stable performance and can still achieve accurate spatial alignment even with the huge nonlinear intensity differences.

In this paper, we describe a fast and efficient method for multi-modal and discontinuity-preserving image registration, implemented on graphics hardware. Multi-sensory data fusion and medical image analysis often pose the challenging task of aligning dense, non-rigid and multi-modal images. However, also optical sequences or stereo image pairs may present variable illumination conditions and noise. The above problems can be addressed by an invariant similarity measure, such as mutual information. Additionally, when using a regularized approach to deal with the ill-posedness of the problem, one has to take care of preserving discontinuities at the motion boundaries. Our approach efficiently addresses the above issues through a primal-dual convex estimation framework, using an approximated Hessian matrix that decouples pixel dependencies, while being asymptotically correct. At the same time, we achieve a high computational efficiency by means of pre-quantized kernel density estimation and differentiation, as well as a parallel implementation on the GPU. Our approach is demonstrated on ground-truth data from the Middlebury database, as well as medical and visible-infrared image pairs.

In this study, we focus on improving the efficiency and accuracy of nonrigid multi-modality registration of medical images. In this regard, we analyze the potentials of using the point similarity measurement approach as an alternative to global computation of mutual information (MI), which is still the most renown multi-modality similarity measure. The improvement capabilities are illustrated using the popular B-spline transformation model. The proposed solution is a combination of three related improvements of the most straightforward implementation, i.e., efficient computation of the voxel displacement field, local estimation of similarity and usage of a static image intensity dependence estimate. Five image registration prototypes were implemented to show contribution and dependence of the proposed improvements. When all the proposed improvements are applied, a significant reduction of computational cost and increased accuracy are obtained. The concept offers additional improvement opportunities by incorporating prior knowledge and machine learning techniques into the static intensity dependence estimation.

The main contribution of this work is a novel set of image features called the virtual circles and their use in the registration of images under similarity transformations. A virtual circle is a circle with maximal radius encompassing a background area that does not contain edge points. It has many useful properties such as its radius, and its dominant edge direction for example, which can be utilized for efficient registration. Furthermore, virtual circles are frequent and can be extracted efficiently with the help of the distance transform from many types of images. We have tested the new virtual circles method in the registration of 66 pairs of images, half of which are printed labels and the other half are indoor scenes. Experimental results have shown that this method has a linear complexity in terms of the number of pixels. It is also highly automatic, because it has a small number of parameters, which almost never need to be changed throughout the experiments.

An automatic elastic medical image registration approach is proposed, based on image intensity. The algorithm is divided into two steps. In Step 1, global affine registration is first used to establish an initial guess and the resulting images can be assumed to have only small local elastic deformations. The mapped images are then used as inputs in Step 2, during which, the study image is modeled as elastic sheet by being divided into sub-images. Moving the individual sub-image in the reference image, the local displacement vectors are found and the global elastic transformation is achieved by assimilating all of the local transformation into a continuous transformation. The algorithm has been validated by simulated data, noisy data and clinical tomographic data. Both experiments and theoretical analysis have demonstrated that the proposed algorithm has a superior computational performance and can register images automatically with an improved accuracy.

This paper presents a semi-automatic registration algorithm for partially overlapped aerial images which has been successfully tested with images of the Mississippi Delta area. In this algorithm, each individual aerial image is registered by employing a pattern search method. This pattern search method considers an affine transformation without shear as a 5-parameter vector and searches toward the gradient direction that results in higher similarity values between the reference and the sensed images. The registration of the first aerial image requires some initial manual work. After the registration of the first image, based on the overlap of the neighboring images and the existing transformation parameters for the first image, the search starting point of the second image can be automatically obtained for the registration of the second image. This process can be repeated for the remaining aerial images in a sequential order. Experimental results with 12 sample images demonstrate the success of this algorithm.

This work proposes a novel keypoint detector called QSIF (Quality and Spatial based Invariant Feature Detector). The primary contributions include: (1) a multilevel box filter is used to build the image scales efficiently and precisely, (2) by examining pixels in quality and spatial space simultaneously, QSIF can directly locate the keypoints without scale space extrema detection in the entire image spatial space, (3) QSIF can precisely control the number of output keypoints while maintaining almost the same repeatability of keypoint detection. This characteristic is essential in many real-time application fields. Extensive experimental results with images under scale, rotation, viewpoint and illumination changes demonstrate that the proposed QSIF has a stable and satisfied repeatability, and it can greatly speed up the keypoint detect and matching.

Image registration is an essential step in many image processing applications that need visual information from multiple images for comparison, integration or analysis. Recently researchers have introduced image registration techniques using the log-polar transform (LPT) for its rotation and scale invariant properties. However, there are two major problems with the LPT based image registration method: inefficient sampling point distribution and high computational cost in the matching procedure. Motivated by the success of LPT based approach, we propose a novel pre-shifted logarithmic spiral (PSLS) approach that distributes the sampling point more efficiently, robust to translation, scale, and rotation. By pre-shifting the sampling point by π/n_θ radian, the total number of samples in the angular direction can be reduced by half. This yields great reduction in computational load in the matching process. Translation between the registered images is recovered with the new search scheme using Gabor feature extraction to accelerate the localization procedure. Experiments on real images demonstrate the effectiveness and robustness of the proposed approach for registering images that are subjected to scale, rotation and translation.

In this paper, we present a binary image registration strategy for the registration of segmented CT scan data of the human head. For the characterization of the 3D skull binary images we adopt a powerful representation of the binary images: the geometric moment invariants (GMIs). They provide pertinent and discriminant information related to the geometry of the binary objects, thereby leading to match points which have similar geometric properties, and also to enhance the quality of the matching process. For the registration algorithm we propose to use the topology-preserving B-spline-based registration method proposed by Noblet et al. for the registration of MRI head images. The algorithm has proven its efficiency and high registration precision. Since the information carried out by the different GMIs is complementary, we study and discuss the importance of combining various GMIs to better guide the matching process. Results obtained using synthetic deformation fields highlight the promising performance of the strategy.

Aerial mapping is attracting more attention due to the development in unmanned aerial vehicles (UAVs) and their availability and also vast applications that require a wide aerial photograph of a region in a specific time. The cross-modality as well as translation, rotation, scale change and illumination are the main challenges in aerial image registration. This paper concentrates on an algorithm for aerial image registration to overcome the aforementioned issues. The proposed method is able to sample automatically and align the sensed images to form the final map. The results are compared with satellite images that shows a reasonable performance with geometrically correct registration.