Image Recovery Method Research Articles

Polarimetric image recovery in turbid media employing circularly polarized light.

Circular polarization memory is a well-known phenomenon indicating that the circular polarization light can persist better its polarization property during propagating through turbid media compared with the linear polarization light. Therefore, in principle, using circularly polarized light can probably improve the quality of image recovery in dense turbid media than using the linearly polarized light. In this paper, we propose a new polarimetric image recovery method in dense turbid media with the illumination light of circular polarization, and we realize the image recovery combining the circular polarization information and linearly polarization information. The real-world experiment results demonstrate that the proposed method is more effective than previous methods, including the traditional polarimetric image recovery method by Schechner's [Appl. Opt.42, 511 (2003)] based on linear polarization.

Polarimetric image recovery method combining histogram stretching for underwater imaging

The underwater imaging could be severely degraded by the scattering media because of the backscattered light and signal attenuation, especially in the case of strong scattering for dense turbid medium. In this paper, we propose an improved method for recovering the underwater image combining the histogram stretching and polarimetric recovery in a proper way. In this method, we stretch the histograms of the orthogonal polarization images while maintaining the polarization relation between them, and then, based on the processed orthogonal polarization images, the recovered image with higher quality can be obtained by the traditional polarimetric recovery method. Several groups of experimental results demonstrate that the quality of underwater images can be effectively enhanced by our method, and its performance is better than that of the traditional polarimetric recovery method. In particular, the proposed method is also quite effective in the condition of dense turbid medium.

Single Image Dehazing With Depth-aware Non-local Total Variation Regularization.

Single image dehazing can benefit many computer vision applications hence has attracted much more attention in recent years. However, it still remains a challenging task due to its double uncertainty of scene transmission and scene radiance. The existing image dehazing methods usually impair edges in the estimated transmission which leads to halo effects in the dehazing results. Besides, most existing methods suffer from noise and artifacts amplification in dense haze region after dehazing. To address these challenges, we propose a transmission adaptive regularized image recovery method for high quality single image dehazing. An initial transmission map is first obtained by a boundary constraint on the haze model. Then it is refined by applying a non-local total variation (NLTV) regularization to keep depth structures while smoothing excessive details. Noticing that the artifacts amplification effect depends on scene transmission, a transmission adaptive regularized recovery method based on NLTV is proposed to simultaneously suppress visual artifacts and preserve image details in the final dehazing result. An efficient alternating optimization algorithm is also proposed to solve the regularization model. Thorough experimental results demonstrate that the proposed method can effectively suppress visual artifacts for degraded hazy images, and yields high-quality results comparative to the state-of-the-art dehazing methods both quantitatively and qualitatively.

Recovery of Degraded-Beyond-Recognition 19th Century Daguerreotypes with Rapid High Dynamic Range Elemental X-ray Fluorescence Imaging of Mercury L Emission

A daguerreotype image, the first commercialized photographic process, is composed of silver-mercury, and often silver-mercury-gold amalgam particles on the surface of a silver-coated copper plate. Specular and diffuse reflectance of light from these image particles produces the range of gray tones that typify these 19th century images. By mapping the mercury distribution with rapid-scanning, synchrotron-based micro-X-ray fluorescence (μ-XRF) imaging, full portraits, which to the naked eye are obscured entirely by extensive corrosion, can be retrieved in a non-invasive, non-contact, and non-destructive manner. This work furthers the chemical understanding regarding the production of these images and suggests that mercury is retained in the image particles despite surface degradation. Most importantly, μ-XRF imaging provides curators with an image recovery method for degraded daguerreotypes, even if the artifact’s condition is beyond traditional conservation treatments.

Dose efficient Compton X-ray microscopy

X-ray imaging techniques have proven invaluable to study biological systems at high resolution due to the penetration power and short wavelength of this radiation. In practice, the resolution and sensitivity of current X-ray imaging techniques are not limited by the performance of optics or image-recovery methods but by radiation damage. We propose the use of Compton (inelastic) X-ray scattering for high-resolution cellular imaging and provide a study of a scanning microscope geometry that requires a dose to achieve a given resolution that is three orders of magnitude lower than for coherent (elastic) scattering. We find that the dose per imaging signal is minimized at a photon energy of 64 keV. This corresponds to a short enough wavelength (0.02 nm) to provide nanometer transverse resolution and micrometer depth of field for tomographic imaging of whole cells. The microscope could be implemented at future high-energy and high-brightness synchrotron-radiation facilities to provide images of unsectioned and unlabeled cells in their native conditions at enough detail to bridge the techniques of super-resolution optical microscopy and cryo-electron microscopy.

Active underwater descattering and image recovery.

Underwater imaging is a promising but challenging topic due to the scattering particles in water, which result in serious light attenuation. Therefore, underwater images suffer from low-contrast and low-resolution issues. In this study, in order to recover high-quality underwater images, the point spread functions (PSFs) are estimated by a slant-edge method. The experiment modulates the illumination source to deal with backscattering and the imager to take two images in orthogonally polarized states. This imaging method benefits the satisfactory edge extraction. The PSF estimation is performed based on the extracted slant edge to enable recovery of the image. In addition, the modulation transfer function (MTF) is introduced to evaluate the resolution variation with the spatial frequencies. It manifests considerable resolution enhancement in the recovered images. Moreover, the proposed underwater image recovery method also reduces the effect from the scattering as an effective compensation to the polarization imaging approach.

ESL-SELO: A robust image denoising algorithm with penalty

Robust image recovery methods have been attracted more and more attention in recent decades for its good property of tolerating system errors or measuring noise. In this paper, we propose a new robust method (ESL-SELO) to recover nosing image, which combine exponential loss function and seamless-L0 (SELO) penalty function to guarantee both accuracy and robustness of the estimator. Theoretical result showed that our method has a local optimal solution and good asymptotic properties. Finally, we compare our method with other methods in simulation which shows better robustness and takes much less time.

Cryptanalysis of an image encryption algorithm based on DNA encoding

Recently an image encryption algorithm based on DNA encoding and the Elliptic Curve Cryptography (ECC) is proposed. This paper aims to investigate the security the DNA-based image encryption algorithm and its resistance against chosen plaintext attack. The results of the analysis demonstrate that security of the algorithm mainly relies on one static shuffling step, with a simple confusion operation. In this study, a practical plain image recovery method is proposed, and it is shown that the images encrypted with the same key could easily be recovered using the suggested cryptanalysis method with as low as two chosen plain images. Also, a strategy to improve the security of the algorithm is presented in this paper.

Curl-Constrained Gradient Estimation for Image Recovery From Highly Incomplete Spectral Data.

In this paper, we introduce new gradient-based methods for image recovery from a small collection of spectral coefficients of the Fourier transform, which is of particular interest for several scanning technologies, such as magnetic resonance imaging. Since gradients of a medical image are much more sparse or compressible than the corresponding image, classical l1 -minimization methods have been used to recover these relative differences. The image values can then be obtained by integration algorithms imposing boundary constraints. Compared with classical gradient recovery methods, we propose two new techniques that improve reconstruction. First, we cast the gradient recovery problem as a compressed sensing problem taking into account that the curl of the gradient field should be zero. Second, inspired by the emerging field of signal processing on graphs, we formulate the gradient recovery problem as an inverse problem on graphs. Iteratively reweighted l1 recovery methods are proposed to recover these relative differences and the structure of the similarity graph. Once the gradient field is estimated, the image is recovered from the compressed Fourier measurements using least squares estimation. Numerical experiments show that the proposed approach outperforms the state-of-the-art image recovery methods.

A Fast Algorithm for Convolutional Structured Low-rank Matrix Recovery.

Fourier domain structured low-rank matrix priors are emerging as powerful alternatives to traditional image recovery methods such as total variation (TV) and wavelet regularization. These priors specify that a convolutional structured matrix, i.e., Toeplitz, Hankel, or their multi-level generalizations, built from Fourier data of the image should be low-rank. The main challenge in applying these schemes to large-scale problems is the computational complexity and memory demand resulting from a lifting the image data to a large scale matrix. We introduce a fast and memory efficient approach called the Generic Iterative Reweighted Annihilation Filter (GIRAF) algorithm that exploits the convolutional structure of the lifted matrix to work in the original un-lifted domain, thus considerably reducing the complexity. Our experiments on the recovery of images from undersampled Fourier measurements show that the resulting algorithm is considerably faster than previously proposed algorithms, and can accommodate much larger problem sizes than previously studied.

Single step full volumetric reconstruction optical coherence tomography utilizing compressive sensing

3D optical coherence tomography imaging (OCT) combined with compressive sensing (CS) has been proved to be an attractive and effective tool in a variety of fields, such as medicine and biology. To achieve high quality imaging while using as less CS sampling rate as possible is the goal of this approach. Here we present an innovative single step fully 3D CS-OCT volumetric image recovery method, in which 3D OCT volumetric image of the object is compressively sampled via our proposed CS coding strategies in all three dimensions while its sparsity is simultaneously taken into consideration in every direction. The object can be directly recovered as the whole volume reconstruction via our advanced full 3D CS reconstruction algorithm. The numerical simulations of a human retina OCT volumetric image reconstruction by our method demonstrate a PSNR of as high as 38dB at a sampling rate of less than 10%.

Directional Frames for Image Recovery: Multi-scale Discrete Gabor Frames

Sparsity-driven image recovery methods assume that images of interest can be sparsely approximated under some suitable system. As discontinuities of 2D images often show geometrical regularities along image edges with different orientations, an effective sparsifying system should have high orientation selectivity. There have been enduring efforts on constructing discrete frames and tight frames for improving the orientation selectivity of tensor product real-valued wavelet bases/frames. In this paper, we studied the general theory of discrete Gabor frames for finite signals, and constructed a class of discrete 2D Gabor frames with optimal orientation selectivity for sparse image approximation. Besides high orientation selectivity, the proposed multi-scale discrete 2D Gabor frames also allow us to simultaneously exploit sparsity prior of cartoon image regions in spatial domain and the sparsity prior of textural image regions in local frequency domain. Using a composite sparse image model, we showed the advantages of the proposed discrete Gabor frames over the existing wavelet frames in several image recovery experiments.

Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis

This paper presents a new depth image recovery method for RGB-D sensors giving a complete, sharp, and accurate object shape from a noisy boundary depth map. The proposed method uses the image guided Total Generalized Variation (TGV) with the depth confidence. A new directional hole filling method of view synthesis is also investigated to produce natural texture in hole regions whereas reducing blurring effect and preventing distortion. Thus, a high-quality image view can be achieved. Experimental results show that the proposed method yields higher quality recovered depth maps and synthesized image views than other previous methods.

A fast patch-dictionary method for whole image recovery

Various algorithms have been proposed for dictionary learning. Among those for image processing, many use image patches to form dictionaries. This paper focuses on whole-image recovery from corrupted linear measurements. We address the open issue of representing an image by overlapping patches: the overlapping leads to an excessive number of dictionary coefficients to determine. With very few exceptions, this issue has limited the applications of image-patch methods to the local kind of tasks such as denoising, inpainting, cartoon-texture decomposition, super-resolution, and image deblurring, for which one can process a few patches at a time. Our focus is global imaging tasks such as compressive sensing and medical image recovery, where the whole image is encoded together, making it either impossible or very ineffective to update a few patches at a time. Our strategy is to divide the sparse recovery into multiple subproblems, each of which handles a subset of non-overlapping patches, and then the results of the subproblems are averaged to yield the final recovery. This simple strategy is surprisingly effective in terms of both quality and speed. In addition, we accelerate computation of the learned dictionary by applying a recent block proximal-gradient method, which not only has a lower per-iteration complexity but also takes fewer iterations to converge, compared to the current state-of-the-art. We also establish that our algorithm globally converges to a stationary point. Numerical results on synthetic data demonstrate that our algorithm can recover a more faithful dictionary than two state-of-the-art methods. Combining our whole-image recovery and dictionary-learning methods, we numerically simulate image inpainting, compressive sensing recovery, and deblurring. Our recovery is more faithful than those of a total variation method and a method based on overlapping patches.

A FAST ALGORITHM FOR STRUCTURED LOW-RANK MATRIX RECOVERY WITH APPLICATIONS TO UNDERSAMPLED MRI RECONSTRUCTION.

Structured low-rank matrix priors are emerging as powerful alternatives to traditional image recovery methods such as total variation (TV) and wavelet regularization. The main challenge in applying these schemes to large-scale problems is the computational complexity and memory demand resulting from a lifting of the image to a high-dimensional dense matrix. We introduce a fast and memory efficient algorithm that exploits the convolutional structure of the lifted matrix to work in the original non-lifted domain, thus considerably reducing the complexity. Our experiments on the recovery of MR images from undersampled measurements show that the resulting algorithm provides improved reconstructions over TV regularization with comparable computation time.

Compressive Sampling Photoacoustic Microscope System based on Low Rank Matrix Completion

Abstract Photoacoustic Microscopy (PAM) has developed into a powerful tool for deep tissue imaging with a better spatial resolution. But the data acquisition time in PAM is so long that it is a great challenge for real time imaging. In this paper, a new PAM data acquisition and image recovery method, called Compressive Sampling PAM System based on Low Rank Matrix Completion (CSLRM-PAM) is proposed to obtain a high-resolution PAM image with relatively low sampling rates. In order to successfully set up a CSLRM-PAM system, the two key problems which we need to keep focus on are design of the compressive sampling scheme and the corresponding image recovery algorithm. In this paper, two compressive sampling schemes based on expander graphs are proposed to replace the conventional point-by-point scanning scheme to implement fast data acquisition. Then, the low rank matrix completion is utilized to obtain high-resolution PAM image directly from the compressive sampling data. The effectiveness of the proposed scheme is validated using both numerical analysis and PAM experiments. In contrast with the conventional system, the proposed CSLRM-PAM system is able to dramatically decrease the total sampling points for a relatively high-resolution PAM image and to implement accelerated data acquisition.

A Multitemporal Profile-Based Interpolation Method for Gap Filling Nonstationary Data

Missing data in Landsat imagery caused by cloud cover and the scan line corrector error confound analysis, and effective methods for gap filling would greatly improve the usability of these data. Several methods for gap filling Landsat data have been proposed, but they typically assume little change in the images being corrected, which is a weakness in change detection applications. We present a profile-based $k$ -nearest-neighbor method for estimating missing spectral index data that provides accurate gap filling under both gradual and abrupt changes. The profile-based interpolator (PBI) uses a multitemporal image sequence and exploits similarities in land cover temporal profiles and spatial relationships to reliably estimate missing data. PBI uses both complete and incomplete pixel profiles to maximize information for estimation and aligns pixel profiles to the target pixel profile to minimize scale biases. For testing, we used eight-image mid-infrared bispectral index sequences from 2009 and 2014 for a study area in eastern Zambia. For ten stratified random samples $(n=\mathbf{1200})$ , we simulated one to six missing values per pixel profile and estimated the missing values at various $k$ values (5–29). Comparison of estimated with original values found results to be highly correlated ( $R^2$ of 0.95–0.72 for one to six missing values, respectively) and precise (mean absolute percent errors of 4%–8%). PBI provided comparable performance to a dictionary learning image recovery method with much better computational efficiency. PBI provides spatially and temporally consistent outputs, preserving abrupt changes in the imagery due to landscape fires even with large data gaps.

Sparse-View CT Image Recovery Using Two-Step Iterative Shrinkage-Thresholding Algorithm

We investigate an image recovery method for sparse-view computed tomography (CT) using an iterative shrinkage algorithm based on a second-order approach. The two-step iterative shrinkage-thresholding (TwIST) algorithm including a total variation regularization technique is elucidated to be more robust than other first-order methods; it enables a perfect restoration of an original image even if given only a few projection views of a parallel-beam geometry. We find that the incoherency of a projection system matrix in CT geometry sufficiently satisfies the exact reconstruction principle even when the matrix itself has a large condition number. Image reconstruction from fan-beam CT can be well carried out, but the retrieval performance is very low when compared to a parallel-beam geometry. This is considered to be due to the matrix complexity of the projection geometry. We also evaluate the image retrieval performance of the TwIST algorithm using measured projection data.

Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks.

We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.

Microwave medical imaging based on sparsity and an iterative method with adaptive thresholding.

We propose a new image recovery method to improve the resolution in microwave imaging applications. Scattered field data obtained from a simplified breast model with closely located targets is used to formulate an electromagnetic inverse scattering problem, which is then solved using the Distorted Born Iterative Method (DBIM). At each iteration of the DBIM method, an underdetermined set of linear equations is solved using our proposed sparse recovery algorithm, IMATCS. Our results demonstrate the ability of the proposed method to recover small targets in cases where traditional DBIM approaches fail. Furthermore, in order to regularize the sparse recovery algorithm, we propose a novel L(2) -based approach and prove its convergence. The simulation results indicate that the L(2)-regularized method improves the robustness of the algorithm against the ill-posed conditions of the EM inverse scattering problem. Finally, we demonstrate that the regularized IMATCS-DBIM approach leads to fast, accurate and stable reconstructions of highly dense breast compositions.