作者：
Lee, Min-HeeYun, Chang-SooKim, KyuseokLee, YoungjinKorea Univ
Ansan Hosp Coll Med Inst Human Genom Study 123 Jeokgeum Ro Ansan Gyeonggi Do South Korea Yonsei Univ
Coll Software & Digital Healthcare Convergence Dept Radiat Convergence Engn 1 Yeonsedae Gil Wonju Gangwon Do South Korea Yonsei Univ
Dept Integrat Med Digital Healthcare Coll Med Seoul South Korea Gachon Univ
Coll Hlth Sci Dept Radiol Sci 191 Hambakmoero Incheon South Korea
The aim of this study was to design an image restoration algorithm that combined denoising and deblurring and to confirm its applicability in positron emission tomography (PET) images of patients with Alzheimer's ...
详细信息
The aim of this study was to design an image restoration algorithm that combined denoising and deblurring and to confirm its applicability in positron emission tomography (PET) images of patients with Alzheimer's disease (AD). PET images of patients with AD obtained using 18F-AV-45, which have a lot of noise, and 18F-FDG, which have a lot of blurring, were available in the Alzheimer's Disease Neuroimaging Initiative open dataset. The proposed framework performed imagerestoration incorporating blind deconvolution after noise reduction using a non-local means (NLM) approach to improve the PET image quality. We found that the coefficient of variation result after denoising and deblurring of the 18F-AV-45 image was improved 1.34 times compared to that for the degraded image. In addition, the profile result of the 18F-FDG PET image of patients with AD, which had a relatively large amount of blurring, showed a gentle shape when deblurring was performed after denoising. The overall no-reference-based evaluation results showed different results according to the degree of noise and blurring in the PET images. In conclusion, the applicability of the deconvolution deblurring algorithm to AD PET images after NLM denoising processing was demonstrated in this study.
Blur and distortion are the primary degradation effects caused by optical aberrations in imaging systems. Traditionally, researchers often treat these two effects as independent issues, leading to separate investigati...
详细信息
Blur and distortion are the primary degradation effects caused by optical aberrations in imaging systems. Traditionally, researchers often treat these two effects as independent issues, leading to separate investigations on deblurring and distortion correction algorithms. However, large field of view (FOV) infrared single-lens systems frequently exhibit coupled aberrations, where blur amplifies distortion and distortion exacerbates image information loss. In such cases, conventional methods often lead to significant optical model deviations and poor restoration performance. To address this issue, we propose an optical coupled imaging model based on point spread function (PSF) peak position mapping, which simulates these coupled effects and enhances the accuracy of large-FOV single-lens imaging simulation. Additionally, we propose a one-step restorationalgorithm for coupled aberrations to simultaneously correct both blur and distortion. Our coupled imaging model is established using differentiable methods, enabling the formation of an end-to-end framework for optical, deblurring, and distortion correction parameters. Through a series of comparative experiments conducted with 40 degrees-80 degrees FOV and the fabrication of a prototype lens with a 19mm focal length, we demonstrate that our method significantly improves image quality in large-FOV single-lens systems and achieves high-resolution imaging in the 8-14 mu m infrared band.
imagerestoration is a research field that attempts to recover a blurred and noisy image. Since it can be modeled as a linear system, we propose in this paper to use the meta-heuristics optimization algorithm Harmony ...
详细信息
ISBN:
(纸本)9781467357609
imagerestoration is a research field that attempts to recover a blurred and noisy image. Since it can be modeled as a linear system, we propose in this paper to use the meta-heuristics optimization algorithm Harmony Search (HS) to find out near-optimal solutions in a Projections Onto Convex Sets-based formulation to solve this problem. The experiments using HS and four of its variants have shown that we can obtain near-optimal and faster restored images than other evolutionary optimization approach.
The goal of deconvolution microscopy for phase-contrast imaging is to reassign the optical blur to its original position and to reduce statistical noise, thus visualizing the cellular structures of living cells in thr...
详细信息
ISBN:
(纸本)9780819496058
The goal of deconvolution microscopy for phase-contrast imaging is to reassign the optical blur to its original position and to reduce statistical noise, thus visualizing the cellular structures of living cells in three dimensions and at subresolution scale. The major features of this technology for a phase-contrast microscopy are discussed through a series of theoretical analyses. A few of possible sources of aberrations and image degradation processes are presented. The theoretical and experimental results have shown that deconvolution microscopy can enhance resolution and contrast by either subtracting or reassigning out-of-focus blur.
In imagerestoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a sparse gradient prior on the whole image,...
详细信息
ISBN:
(纸本)9781424469840;9781424469857
In imagerestoration tasks, a heavy-tailed gradient distribution of natural images has been extensively exploited as an image prior. Most image restoration algorithms impose a sparse gradient prior on the whole image, reconstructing an image with piecewise smooth characteristics. While the sparse gradient prior removes ringing and noise artifacts, it also tends to remove mid-frequency textures, degrading the visual quality. We can attribute such degradations to imposing an incorrect image prior. The gradient profile in fractal-like textures, such as trees, is close to a Gaussian distribution, and small gradients from such regions are severely penalized by the sparse gradient prior. To address this issue, we introduce an image restoration algorithm that adapts the image prior to the underlying texture. We adapt the prior to both low-level local structures as well as mid-level textural characteristics. Improvements in visual quality is demonstrated on deconvolution and demising tasks.
Recently, super-resolution imagerestoration theory develops rapidly. If the image degradation process is not reversible, super-resolution image restoration algorithm might use a priori limited degradation parameters,...
详细信息
ISBN:
(纸本)081945592X
Recently, super-resolution imagerestoration theory develops rapidly. If the image degradation process is not reversible, super-resolution image restoration algorithm might use a priori limited degradation parameters, under the condition that the image low frequency information in frequency-pass bands can be restored, to restore blurred images by restoring high frequencies beyond the cut-off frequency. Therefore image details can be retrieved so much that the restored image is greatly close to the original object~[1,2]. It is practical to image reconstruction.
The distribution of edge values for an image of a general scene often has a sharp peak with a long tail. This property, which can be well described by a Lorentzian probability function, has been used to develop an eff...
详细信息
The distribution of edge values for an image of a general scene often has a sharp peak with a long tail. This property, which can be well described by a Lorentzian probability function, has been used to develop an efficient nonlinear image restoration algorithm for reducing the various artifacts that often arise in the restored images. The algorithm starts with a Wiener filter solution which is used to model the edge image by the Lorentzian function so that the likelihood of the image can be estimated. A nonlinear correction term is then introduced which increases this image likelihood under the mean square error criterion. This process ensures that the resulting image retains its sharpness while reducing the noise and ringing artifacts. An iterative procedure has been developed to implement this method. Computer simulated results show that the algorithm is robust in reducing artifacts and easily implemented. The algorithm also possesses a superresolution capability due to the highly nonlinear property of the correction term.
暂无评论