scholarly journals A Cost Function for the Uncertainty of Matching Point Distribution on Image Registration

2021 ◽  
Vol 10 (7) ◽  
pp. 438
Author(s):  
Yuxia Bian ◽  
Meizhen Wang ◽  
Yongbin Chu ◽  
Zhihong Liu ◽  
Jun Chen ◽  
...  
Keyword(s):  
Computer Vision ◽  
Fixed Point ◽  
Image Registration ◽  
Cost Function ◽  
Point Distribution ◽  
Dilution Of Precision ◽  
Point Position ◽  
Position Accuracy ◽  
The Relationship ◽  
Overlapping Region

Computing the homography matrix using the known matching points is a key step in computer vision for image registration. In practice, the number, accuracy, and distribution of the known matching points can affect the uncertainty of the homography matrix. This study mainly focuses on the effect of matching point distribution on image registration. First, horizontal dilution of precision (HDOP) is derived to measure the influence of the distribution of known points on fixed point position accuracy on the image. The quantization function, which is the average of the center points’ HDOP* of the overlapping region, is then constructed to measure the uncertainty of matching distribution. Finally, the experiments in the field of image registration are performed to verify the proposed function. We test the consistency of the relationship between the proposed function and the average of symmetric transfer errors. Consequently, the proposed function is appropriate for measuring the uncertainty of matching point distribution on image registration.

scholarly journals Quantification Method for the Uncertainty of Matching Point Distribution on 3D Reconstruction

2020 ◽  
Vol 9 (4) ◽  
pp. 187
Author(s):  
Yuxia Bian ◽  
Xuejun Liu ◽  
Meizhen Wang ◽  
Hongji Liu ◽  
Shuhong Fang ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
Point Cloud ◽  
Point Distribution ◽  
Multiple Images ◽  
Quantification Method ◽  
Real Scene ◽  
Direct Data ◽  
The Relationship ◽  
Overlapping Region

Matching points are the direct data sources of the fundamental matrix, camera parameters, and point cloud calculation. Thus, their uncertainty has a direct influence on the quality of image-based 3D reconstruction and is dependent on the number, accuracy, and distribution of the matching points. This study mainly focuses on the uncertainty of matching point distribution. First, horizontal dilution of precision (HDOP) is used to quantify the feature point distribution in the overlapping region of multiple images. Then, the quantization method is constructed. H D O P ∗ ¯ , the average of 2 × arctan ( H D O P × n 5 − 1 ) / π on all images, is utilized to measure the uncertainty of matching point distribution on 3D reconstruction. Finally, simulated and real scene experiments were performed to describe and verify the rationality of the proposed method. We found that the relationship between H D O P ∗ ¯ and the matching point distribution in this study was consistent with that between matching point distribution and 3D reconstruction. Consequently, it may be a feasible method to predict the quality of 3D reconstruction by calculating the uncertainty of matching point distribution.

Computing the Medical Image Registration Using Meta-Heuristics

2014 ◽  
Vol 643 ◽  
pp. 237-242 ◽  
Author(s):  
Tahari Abdou El Karim ◽  
Bendakmousse Abdeslam ◽  
Ait Aoudia Samy
Keyword(s):  
Image Processing ◽  
Genetic Algorithms ◽  
Simulated Annealing ◽  
Image Registration ◽  
Cost Function ◽  
Population Genetic ◽  
Medical Image ◽  
Medical Image Registration ◽  
Anatomical Structures

The image registration is a very important task in image processing. In the field of medical imaging, it is used to compare the anatomical structures of two or more images taken at different time to track for example the evolution of a disease. Intensity-based techniques are widely used in the multi-modal registration. To have the best registration, a cost function expressing the similarity between these images is maximized. The registration problem is reduced to the optimization of a cost function. We propose to use neighborhood meta-heuristics (tabu search, simulated annealing) and a meta-heuristic population (genetic algorithms). An evaluation step is necessary to estimate the quality of registration obtained. In this paper we present some results of medical image registration

scholarly journals Nonrigid Medical Image Registration Using an Information Theoretic Measure Based on Arimoto Entropy with Gradient Distributions

Entropy ◽  
2019 ◽  
Vol 21 (2) ◽  
pp. 189 ◽  
Author(s):  
Bicao Li ◽  
Huazhong Shu ◽  
Zhoufeng Liu ◽  
Zhuhong Shao ◽  
Chunlei Li ◽  
...  
Keyword(s):  
Image Registration ◽  
Cost Function ◽  
Medical Image ◽  
Spatial Information ◽  
Brain Magnetic Resonance Imaging ◽  
Dissimilarity Measure ◽  
Medical Image Registration ◽  
Three Dimension ◽  
Information Theoretic ◽  
Regularization Term

This paper introduces a new nonrigid registration approach for medical images applying an information theoretic measure based on Arimoto entropy with gradient distributions. A normalized dissimilarity measure based on Arimoto entropy is presented, which is employed to measure the independence between two images. In addition, a regularization term is integrated into the cost function to obtain the smooth elastic deformation. To take the spatial information between voxels into account, the distance of gradient distributions is constructed. The goal of nonrigid alignment is to find the optimal solution of a cost function including a dissimilarity measure, a regularization term, and a distance term between the gradient distributions of two images to be registered, which would achieve a minimum value when two misaligned images are perfectly registered using limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) optimization scheme. To evaluate the test results of our presented algorithm in non-rigid medical image registration, experiments on simulated three-dimension (3D) brain magnetic resonance imaging (MR) images, real 3D thoracic computed tomography (CT) volumes and 3D cardiac CT volumes were carried out on elastix package. Comparison studies including mutual information (MI) and the approach without considering spatial information were conducted. These results demonstrate a slight improvement in accuracy of non-rigid registration.

Radial subsampling for fast cost function computation in intensity-based 3D image registration

2007 ◽  
Author(s):  
Thomas Boettger ◽  
Ivo Wolf ◽  
Hans-Peter Meinzer ◽  
Juan Carlos Celi
Keyword(s):  
Image Registration ◽  
Cost Function ◽  
3D Image ◽  
Function Computation ◽  
3D Image Registration

scholarly journals SUBPIXEL IMAGE REGISTRATION USING CIRCULAR FIDUCIALS

1994 ◽  
Vol 04 (04) ◽  
pp. 403-422 ◽  
Author(s):  
ALON EFRAT ◽  
CRAIG GOTSMAN
Keyword(s):  
Computer Vision ◽  
Number Theory ◽  
Image Registration ◽  
Practical Importance ◽  
Efficient Algorithms ◽  
Automatic Inspection ◽  
Rotation Invariant ◽  
Registration Accuracy ◽  
Geometric Methods ◽  
Lattice Geometry

The design of fiducials for precise image registration is of major practical importance in computer vision, especially in automatic inspection applications. We analyze the sub-pixel registration accuracy that can, and cannot, be achieved by some rotation-invariant fiducials, and present and analyze efficient algorithms for the registration procedure. We rely on some old and new results from lattice geometry and number theory and efficient computational-geometric methods.

An Efficient Numerical Method for Mean Curvature-Based Image Registration Model

2017 ◽  
Vol 7 (1) ◽  
pp. 125-142 ◽  
Author(s):  
Jin Zhang ◽  
Ke Chen ◽  
Fang Chen ◽  
Bo Yu
Keyword(s):  
Fixed Point ◽  
Image Quality ◽  
Image Registration ◽  
Mean Curvature ◽  
Numerical Experiments ◽  
Energy Functional ◽  
Linear Search ◽  
Multilevel Method ◽  
Solution Approach ◽  
Newton Scheme

AbstractMean curvature-based image registration model firstly proposed by Chumchob-Chen-Brito (2011) offered a better regularizer technique for both smooth and nonsmooth deformation fields. However, it is extremely challenging to solve efficiently this model and the existing methods are slow or become efficient only with strong assumptions on the smoothing parameterβ. In this paper, we take a different solution approach. Firstly, we discretize the joint energy functional, following an idea of relaxed fixed point is implemented and combine with Gauss-Newton scheme with Armijo's Linear Search for solving the discretized mean curvature model and further to combine with a multilevel method to achieve fast convergence. Numerical experiments not only confirm that our proposed method is efficient and stable, but also it can give more satisfying registration results according to image quality.

scholarly journals Interactive Multigrid Refinement for Deformable Image Registration

2013 ◽  
Vol 2013 ◽  
pp. 1-9
Author(s):  
Wu Zhou ◽  
Yaoqin Xie
Keyword(s):  
Image Registration ◽  
Medical Images ◽  
Salient Feature ◽  
Deformable Image Registration ◽  
Free Form ◽  
Reference Image ◽  
Free Form Deformation ◽  
Feature Based ◽  
Automatic Algorithm ◽  
Overlapping Region

Deformable image registration is the spatial mapping of corresponding locations between images and can be used for important applications in radiotherapy. Although numerous methods have attempted to register deformable medical images automatically, such as salient-feature-based registration (SFBR), free-form deformation (FFD), and demons, no automatic method for registration is perfect, and no generic automatic algorithm has shown to work properly for clinical applications due to the fact that the deformation field is often complex and cannot be estimated well by current automatic deformable registration methods. This paper focuses on how to revise registration results interactively for deformable image registration. We can manually revise the transformed image locally in a hierarchical multigrid manner to make the transformed image register well with the reference image. The proposed method is based on multilevel B-spline to interactively revise the deformable transformation in the overlapping region between the reference image and the transformed image. The resulting deformation controls the shape of the transformed image and produces a nice registration or improves the registration results of other registration methods. Experimental results in clinical medical images for adaptive radiotherapy demonstrated the effectiveness of the proposed method.

EFFICIENT INVARIANT IMAGE REGISTRATION UTILIZING PRE-SHIFTED LOGARITHMIC SPIRAL

2010 ◽  
Vol 10 (03) ◽  
pp. 395-421
Author(s):  
RITTAVEE MATUNGKA ◽  
YUAN F. ZHENG ◽  
ROBERT L. EWING
Keyword(s):  
Image Registration ◽  
Visual Information ◽  
Computational Cost ◽  
Logarithmic Spiral ◽  
Sampling Point ◽  
Scale Invariant ◽  
Point Distribution ◽  
Registration Method ◽  
Gabor Feature ◽  
Gabor Feature Extraction

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/nθ 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.

scholarly journals A dose based metric to assess the accuracy of image registration

2021 ◽  
Author(s):  
Stacy-Lee Annis
Keyword(s):  
Image Registration ◽  
Mapping Method ◽  
Registration Error ◽  
Registration Errors ◽  
Dose Mapping ◽  
The Difference ◽  
Energy Mapping ◽  
The Relationship

The relationship between dose mapped using two mapping methods (energy mapping method and voxel warping method) and registration error was examined. The correlation between the difference in doses mapped using these methods, defined as dose mapping difference (DMD), and landmark distance to agreement for a realistic lung patient plan using registrations of varying accuracy was examined. Results showed no correlation between DMD and landmark error. Further investigation on simple dose mapping geometries revealed a correlation of DMD with fractional volume (FVC) change induced by registration errors. A formula for DMD as a function of FVC was derived. Results of this formula agreed with simulated values of DMD with percentage differences less than 3.5% in regions of uniform dose. However, no agreement was found in regions containing a dose gradient. Further work is required in order to extend this formula to regions of dose gradients and scenarios that emulate realistic deformations.

Sign in / Sign up

Export Citation Format

Share Document