Similarity transformation parameters recovery based on Radon transform. Application in image registration and object recognition

Perfect image registration is an unsolved challenge that has been attempted in a multitude of different ways. This paper presents an approach for single-modal, multi-view registration of aerial imagery data that uses bandelets in the preprocessing phase to extract key geometric features and limit the amount of details in the image that must be considered during the feature matching process. Applying the bandelet decomposition on both the reference and target images before feature extraction will limit the control point selection process to only those points with the most relevant geometric data. The approach uses a multi-scale approach to estimate a transformation that converges to an optimal solution as well as reduce the computation time for real-time image registration. The bandelet basis also provides for a more effective feature (e.g. corner) detection and extraction method because it determines the geometric flow and allows for shifted patches in the orthogonal direction of the geometric flow. Theoretically the bandelet results in less false positives and better detection rates than existing methods. The Bandelet-based Image Registration (BIR) method has applications in image fusion, change detection, object recognition, autonomous navigation, and target tracking.

Continuum mechanical models have been used to regularize ill-posed problems in many applications in medical imaging analysis such as image registration and left ventricular motion estimation. In this work, we present a significant extension to the common elastic model which we call the active elastic model. The active elastic model is designed to reduce bias in deformation estimation and to allow the imposition of proper priors on deformation estimation problems that contain information regarding both the expected magnitude and the expected variability of the deformation to be estimated. We test this model on the problem of left ventricular deformation estimation, and present ideas for its application in image registration and brain deformation during neurosurgery.KeywordsImage RegistrationElastic ModelActive Shape ModelMedical Image AnalysisPassive ModelThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Objective To investigate the application of CT image and cone beam computed tomography (CBCT) image registration based on 3D Slicer software in image-guided radiotherapy for uterine cervical neoplasms. Methods Based on 3D Slicer software and Slicer RT toolkit, 10 positioning CT images and 50 CBCT images of 10 patients with uterine cervical neoplasms in Henan Provincial People's Hospital between January 2018 and October 2018 had rigid registration and b-spline deformation registration respectively. The dice similarity coefficient (DSC) and Hausdorff distance (HD) of the bladder, rectum, femoral head, spinal cord, and body of CT-CBCT images were compared by using paired t-test before and after the registration. Results Pre-registration, rigid registration and after b-spline deformation registration of CT images and CBCT images, the DSC in the bladder (0.459±0.177, 0.528±0.184, 0.542±0.187, respectively), the rectum (0.564±0.141, 0.632±0.091, 0.684±0.097, respectively), the femoral head (0.695±0.088, 0.833±0.030, 0.865±0.027, respectively), the spinal cord (0.587±0.119, 0.746±0.085, 0.834±0.032, respectively) and the body surface (0.922±0.013, 0.948±0.011, 0.959±0.009, respectively) showed an increased trend; HD in the bladder (12.8±7.2, 12.2±7.1, 11.7±7.3, respectively), the rectum (5.0±1.8, 4.4±1.2, 3.4±1.2, respectively), the femoral head (3.6±1.2, 1.8±0.5, 1.5±0.5, respectively), the spinal cord (4.0±1.0, 2.7±1.3, 1.8±0.5, respectively) and the body surface (6.3±2.1, 5.2±2.0, 4.3±2.0, respectively) showed a decreased trend. The differences of pairwise comparison in the same parts were statistically significant (all P < 0.05). Conclusions Both rigid registration and b-spline deformation registration of CT-CBCT images based on 3D Slicer software can improve the radiotherapy accuracy of uterine cervical neoplasms, and b-spline deformation registration has more significant advantages. Key words: Uterine cervical neoplasms; Radiotherapy; 3D Slicer software; Cone-beam computed tomography; Image registration; Image-guided radiation therapy

Distance transforms (DTs) are standard tools in image analysis, with applications in image registration and segmentation. The DT is based on extremal (minimal) distance values and is therefore highly sensitive to noise. We present a stochastic distance transform (SDT) based on discrete random sets, in which a model of element-wise probability is utilized and the SDT is computed as the first moment of the distance distribution to the random set. We present two methods for computing the SDT and analyze them w.r.t. accuracy and complexity. Further, we propose a method, utilizing kernel density estimation, for estimating probability functions and associated random sets to use with the SDT. We evaluate the accuracy of the SDT and the proposed framework on images of thin line structures and disks corrupted by salt and pepper noise and observe excellent performance. We also insert the SDT into a segmentation framework and apply it to overlapping objects, where it provides substantially improved performance over previous methods. Finally, we evaluate the SDT and observe very good performance, on simulated images from localization microscopy, a state-of-the-art super-resolution microscopy technique which yields highly spatially localized but noisy point-clouds.

For numerous applications in image registration, sub-pixel translation estimation is a fundamental task, and increasing attention has been given to methods based on image phase information. However, we have found that none of these methods is universal. In other words, for any one of these methods, we can always find some image pairs which will not be well matched. In this paper, by introducing the cyclic shift matrix (CSM), we present a new model for the translation matching problem and derive a least squares solution for the model. In addition, by repeatedly applying the CSM to the matching image, an iterative CSM method is proposed to further improve the matching accuracy. Furthermore, we show that the traditional phase-based matching algorithms can only achieve an exact solution when there is a cyclic shift relationship between the images to be matched. The proposed method is evaluated using simulated and real images and demonstrates a better performance in both accuracy and robustness compared with the state-of-the-art methods.

We will demonstrate object recognition performed by a Sony Aibo robot dog. The dog is connected to a wide-area grid system consisting of hundreds of computers located at several institutes in Europe. Object recognition is obtained by matching local histograms of color invariant features against a learned database. We effectively decompose object appearance recognition into a view based (learned) part and an appearance (invariant) part. Invariance deals with lighting conditions, color constancy, and robustness against shading effects and cast shadows. A learned set of object views guarantees recognition of different aspects of the object. As such, we show state-of-the-art in object recognition in images, as well as state-of-the-art in multimedia grid computing, merged together into a single application

In this paper, we describe improvements to the particle swarm optimizer (PSO) made by the inclusion of an unscented Kalman filter to guide particle motion. We show how this method increases the speed of convergence, and reduces the likelihood of premature convergence, increasing the overall accuracy of optimization. We demonstrate the effectiveness of the unscented Kalman filter PSO by comparing it with the original PSO algorithm and its variants designed to improve the performance. The PSOs were tested firstly on a number of common synthetic benchmarking functions and secondly applied to a practical three-dimensional image registration problem. The proposed methods displayed better performances for 4 out of 8 benchmark functions and reduced the target registration errors by at least 2mm when registering down-sampled benchmark brain images. They also demonstrated an ability to align images featuring motion-related artifacts which all other methods failed to register. These new PSO methods provide a novel, efficient mechanism to integrate prior knowledge into each iteration of the optimization process, which can enhance the accuracy and speed of convergence in the application of medical image registration.

Image registration is the process of aligning images.1,2 During interventional procedures to deliver electrical therapy, the catheters or leads are usually manipulated under the guidance of a fluoroscopy system. Typically,...

The Recognition and Classification of Objects Based on the Modified Distance Metric

In the last few decades, image registration (IR) has been established as a very active research area in computer vision. Over the years, IR's applications cover a broad range of real-world problems including remote sensing, medical imaging, artificial vision, and computer-aided design. In particular, medical IR is a mature research field with theoretical support and two decades of practical experience. Traditionally, medical IR has been tackled by iterative approaches considering numerical optimization methods which are likely to get stuck in local optima. Recently, a large number of medical IR methods based on the use of metaheuristics such as evolutionary algorithms have been proposed providing outstanding results. The success of the latter modern search methods is related to their ability to perform an effective and efficient global search in complex solution spaces like those tackled in the IR discipline. In this contribution, we aim to develop an experimental survey of the most recognized feature-based medical IR methods considering evolutionary algorithms and other metaheuristics. To do so, the generic IR framework is first presented by providing a deep description of the involved components. Then, a large number of the latter proposals are reviewed. Finally, the most representative methods are benchmarked on two real-world medical scenarios considering two data sets of three-dimensional images with different modalities.

Influence of additive noise on noise-induced phase transitions in nonlinear chains

In digital image processing, template matching is a process to determine the location of sub image inside an image. The sub image, which is called template, usually has similarity with a part of the image. The template can be in different size, color or form. Template matching is famously used in image registration and object recognition. In this paper, we focus on the performance of the Sum of Squared Differences (SSD) and Normalized Cross Correlation (NCC)as the techniques that used in image registration for matching the template with an image. This experiment is aiming to compare the ability of both techniques in term of quality of output image as well as the time taken in execution process. Furthermore, it also to test the effect of template image to output image when there is noise and rotation. This paper provides an explanation about the concept of similarity measure techniques and how the algorithms are implementing in image registration process. Finally, the performance of these methods is tested by making comparison based on the value of correlation coefficient that produced from different image templates.

A comparative interpretation of mammograms has become increasingly important, and it is crucial to develop subtraction processing and registration methods for mammograms. However, nonrigid image registration has seldom been applied to subjects constructed with soft tissue only, such as mammograms. We examined whether subtraction processing for the comparative interpretation of mammograms can be performed using nonrigid image registration. As a preliminary study, we evaluated the results of subtraction processing by applying nonrigid image registration to normal mammograms, assuming a comparative interpretation between the left and right breasts. Mediolateral-oblique-view mammograms were taken from noncancer patients and divided into 1000 cases for training, 100 cases for validation, and 500 cases for testing. Nonrigid image registration was applied to align the horizontally flipped left-breast mammogram with the right one. We compared the sum of absolute differences (SAD) of the difference of bilateral images (Difference Image) with and without the application of nonrigid image registration. Statistically, the average SAD was significantly lower with the application of nonrigid image registration than without it (without: 0.0692; with: 0.0549 (p < 0.001)). In four subgroups using the breast area, breast density, compressed breast thickness, and Difference Image without nonrigid image registration, the average SAD of the Difference Image was also significantly lower with nonrigid image registration than without it (p < 0.001). Nonrigid image registration was found to be sufficiently useful in aligning bilateral mammograms, and it is expected to be an important tool in the development of a support system for the comparative interpretation of mammograms.

Existing learning-based image registration methods learn a network that outputs a spatial transformation to warp a source image to align to the target image, which is carried out through optimizing matching similarities. Such matching criteria are mostly agnostic of regions. However, in many applications of medical image registration, the correspondence with specific regions of interest (ROIs) such as organs in source and target images is more important than the whole images as not all regions are equal. Motivated by this, we hereby propose a segmentation-assisted registration network to emphasize the ROIs more. We promote the estimation of registration fields by encoding the anatomical structure extracted by manual or predicted segmentation label generated from fusing the outputs of a multi-atlas-based registration model and a deep segmentation network which is trained using a few manual labeled images. The experiments on 3D brain MRI indicate that our approach improves the registration performance with few manual segmentation labels or ROIs. Our approach also outputs competitive segmentation results.

Maximization of mutual information (MI) (MMI) has a wide application in multimodal image registration. The conventional MMI algorithm is based on the statistics derived from image sampling and does not use spatial features. In this paper, we proposed an improved MMI registration algorithm that combines the spatial information through a feature-based selection mechanism. A Harris corner filter is chosen to classify the pixels. The classification results are used to focus sample selection, joint entropy estimation, and weighted MI information calculation. Although features play an important role, conventional feature matching is not used, which removes an important challenge to the use of feature-based information. The advantages of the proposed algorithm are improved robustness by incorporation of spatial features and significant reduction in computing time for registration. Experiments with challenging synthetic images and multimodal airborne infrared images are provided to demonstrate the improvement.