Face hallucination or super-resolution is an inverse problem which is underdetermined,and the compressive sensing(CS)theory provides an effective way of seeking inverse problem solutions.In this paper,a novel compress...Face hallucination or super-resolution is an inverse problem which is underdetermined,and the compressive sensing(CS)theory provides an effective way of seeking inverse problem solutions.In this paper,a novel compressive sensing based face hallucination method is presented,which is comprised of three steps:dictionary learning、sparse coding and solving maximum a posteriori(MAP)formulation.In the first step,the K-SVD dictionary learning algorithm is adopted to obtain a dictionary which can sparsely represent high resolution(HR)face image patches.In the second step,we seek the sparsest representation for each low-resolution(LR)face image paches input using the learned dictionary,super resolution image blocks are obtained from the sparsest coefficients and dictionaries,which then are assembled into super-resolution(SR)image.Finally,MAP formulation is introduced to satisfy the consistency restrictive condition and obtain the higher quality HR images.The experimental results demonstrate that our approach can achieve better super-resolution faces compared with other state-of-the-art method.展开更多
Single image super-resolution(SISR)is a fundamentally challenging problem because a low-resolution(LR)image can correspond to a set of high-resolution(HR)images,while most are not expected.Recently,SISR can be achieve...Single image super-resolution(SISR)is a fundamentally challenging problem because a low-resolution(LR)image can correspond to a set of high-resolution(HR)images,while most are not expected.Recently,SISR can be achieved by a deep learning-based method.By constructing a very deep super-resolution convolutional neural network(VDSRCNN),the LR images can be improved to HR images.This study mainly achieves two objectives:image super-resolution(ISR)and deblurring the image from VDSRCNN.Firstly,by analyzing ISR,we modify different training parameters to test the performance of VDSRCNN.Secondly,we add the motion blurred images to the training set to optimize the performance of VDSRCNN.Finally,we use image quality indexes to evaluate the difference between the images from classical methods and VDSRCNN.The results indicate that the VDSRCNN performs better in generating HR images from LR images using the optimized VDSRCNN in a proper method.展开更多
A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images,...A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images, and divide these patch pairs into different groups by K-means clustering. Then, we learn an over-complete sub-dictionary pair offline from corresponding group patch pairs. For a given low-resolution patch, we adaptively select one sub-dictionary to reconstruct the high resolution patch online. In addition, non-local self-similarity and steering kernel regression constraints are integrated into patch aggregation to improve the quality of the recovered images. Experiments show that the proposed method is able to realize state-of-the-art performance in terms of both objective evaluation and visual perception.展开更多
This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-re...This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-resolution problem in solving Gauss process; further use sparse algorithm, not only it can optimize the super parameter of Gauss kernel function, but also to optimize the initial entry training, so as to obtain more accurate regression Gauss process. Experimental results show that： the paper proposed algorithm can does not reduce the image reconstruction results, and it can reduce the computational complexity.展开更多
A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. F...A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function （PSF） matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar （SAR） images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio （SNR）. Five versions of SVD algorithms, namely 1 ） using all singular values, 2） using the top 80% singular values, 3） using the top 50% singular values, 4） using the top 20% singular values and 5） using singular values s such that S2≥/max（s2）/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/（rinSNR）1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.展开更多
Intravascular ultrasound( IVUS) is an important imaging technique that is used to study vascular wall architecture for diagnosis and assessment of the vascular diseases. Segmentation of lumen and media-adventitia boun...Intravascular ultrasound( IVUS) is an important imaging technique that is used to study vascular wall architecture for diagnosis and assessment of the vascular diseases. Segmentation of lumen and media-adventitia boundaries from IVUS images is a basic and necessary step for quantitative assessment of the vascular walls.Due to ultrasound speckles, artifacts and individual differences,automated segmentation of IVUS images represents a challenging task. In this paper,a random walk based method is proposed for fully automated segmentation of IVUS images. Robust and accurate determination of the seed points for different regions is the key to successful use of the random walk algorithm in segmentation of IVUS images and is the focus of the present work. Performance of the proposed algorithm was evaluated over an image database with 900 IVUS image frames of nine patient cases. The preliminary experimental results show the potential of the proposed IVUS image segmentation approach.展开更多
Superresolution is an image processing technique that estimates an original high-resolutionimage from its low-resolution and degraded observations.In superresolution tasks,there have beenproblems regarding the computa...Superresolution is an image processing technique that estimates an original high-resolutionimage from its low-resolution and degraded observations.In superresolution tasks,there have beenproblems regarding the computational cost for the estimation of high-dimensional variables.Theseproblems are now being overcome by the recent development of fast computers and the developmentof powerful computational techniques such as variational Bayesian approximation.This paper reviewsa Bayesian treatment of the superresolution problem and presents its extensions based on hierarchicalmodeling by employing hidden variables.展开更多
文摘Face hallucination or super-resolution is an inverse problem which is underdetermined,and the compressive sensing(CS)theory provides an effective way of seeking inverse problem solutions.In this paper,a novel compressive sensing based face hallucination method is presented,which is comprised of three steps:dictionary learning、sparse coding and solving maximum a posteriori(MAP)formulation.In the first step,the K-SVD dictionary learning algorithm is adopted to obtain a dictionary which can sparsely represent high resolution(HR)face image patches.In the second step,we seek the sparsest representation for each low-resolution(LR)face image paches input using the learned dictionary,super resolution image blocks are obtained from the sparsest coefficients and dictionaries,which then are assembled into super-resolution(SR)image.Finally,MAP formulation is introduced to satisfy the consistency restrictive condition and obtain the higher quality HR images.The experimental results demonstrate that our approach can achieve better super-resolution faces compared with other state-of-the-art method.
文摘Single image super-resolution(SISR)is a fundamentally challenging problem because a low-resolution(LR)image can correspond to a set of high-resolution(HR)images,while most are not expected.Recently,SISR can be achieved by a deep learning-based method.By constructing a very deep super-resolution convolutional neural network(VDSRCNN),the LR images can be improved to HR images.This study mainly achieves two objectives:image super-resolution(ISR)and deblurring the image from VDSRCNN.Firstly,by analyzing ISR,we modify different training parameters to test the performance of VDSRCNN.Secondly,we add the motion blurred images to the training set to optimize the performance of VDSRCNN.Finally,we use image quality indexes to evaluate the difference between the images from classical methods and VDSRCNN.The results indicate that the VDSRCNN performs better in generating HR images from LR images using the optimized VDSRCNN in a proper method.
基金partially supported by the National Natural Science Foundation of China under Grants No. 61071146, No. 61171165the Natural Science Foundation of Jiangsu Province under Grant No. BK2010488+1 种基金sponsored by Qing Lan Project, Project 333 "The Six Top Talents" of Jiangsu Province
文摘A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images, and divide these patch pairs into different groups by K-means clustering. Then, we learn an over-complete sub-dictionary pair offline from corresponding group patch pairs. For a given low-resolution patch, we adaptively select one sub-dictionary to reconstruct the high resolution patch online. In addition, non-local self-similarity and steering kernel regression constraints are integrated into patch aggregation to improve the quality of the recovered images. Experiments show that the proposed method is able to realize state-of-the-art performance in terms of both objective evaluation and visual perception.
文摘This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-resolution problem in solving Gauss process; further use sparse algorithm, not only it can optimize the super parameter of Gauss kernel function, but also to optimize the initial entry training, so as to obtain more accurate regression Gauss process. Experimental results show that： the paper proposed algorithm can does not reduce the image reconstruction results, and it can reduce the computational complexity.
基金Project(2008041001) supported by the Academician Foundation of China Project(N0601-041) supported by the General Armament Department Science Foundation of China
文摘A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function （PSF） matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar （SAR） images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio （SNR）. Five versions of SVD algorithms, namely 1 ） using all singular values, 2） using the top 80% singular values, 3） using the top 50% singular values, 4） using the top 20% singular values and 5） using singular values s such that S2≥/max（s2）/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/（rinSNR）1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.
基金Innovation Program of Shanghai Municipal Education Commission,China(No.13YZ136)National Science&Technology Support Program during the 12th Five-Year Plan Period of China(No.2012BAI13B02)
文摘Intravascular ultrasound( IVUS) is an important imaging technique that is used to study vascular wall architecture for diagnosis and assessment of the vascular diseases. Segmentation of lumen and media-adventitia boundaries from IVUS images is a basic and necessary step for quantitative assessment of the vascular walls.Due to ultrasound speckles, artifacts and individual differences,automated segmentation of IVUS images represents a challenging task. In this paper,a random walk based method is proposed for fully automated segmentation of IVUS images. Robust and accurate determination of the seed points for different regions is the key to successful use of the random walk algorithm in segmentation of IVUS images and is the focus of the present work. Performance of the proposed algorithm was evaluated over an image database with 900 IVUS image frames of nine patient cases. The preliminary experimental results show the potential of the proposed IVUS image segmentation approach.
文摘Superresolution is an image processing technique that estimates an original high-resolutionimage from its low-resolution and degraded observations.In superresolution tasks,there have beenproblems regarding the computational cost for the estimation of high-dimensional variables.Theseproblems are now being overcome by the recent development of fast computers and the developmentof powerful computational techniques such as variational Bayesian approximation.This paper reviewsa Bayesian treatment of the superresolution problem and presents its extensions based on hierarchicalmodeling by employing hidden variables.
