Image Recovery Process Research Articles

DarwinGSE: Towards better image retrieval systems for intellectual property datasets.

A trademark's image is usually the first type of indirect contact between a consumer and a product or a service. Companies rely on graphical trademarks as a symbol of quality and instant recognition, seeking to protect them from copyright infringements. A popular defense mechanism is graphical searching, where an image is compared to a large database to find potential conflicts with similar trademarks. Despite not being a new subject, image retrieval state-of-the-art lacks reliable solutions in the Industrial Property (IP) sector, where datasets are practically unrestricted in content, with abstract images for which modeling human perception is a challenging task. Existing Content-based Image Retrieval (CBIR) systems still present several problems, particularly in terms of efficiency and reliability. In this paper, we propose a new CBIR system that overcomes these major limitations. It follows a modular methodology, composed of a set of individual components tasked with the retrieval, maintenance and gradual optimization of trademark image searching, working on large-scale, unlabeled datasets. Its generalization capacity is achieved using multiple feature descriptions, weighted separately, and combined to represent a single similarity score. Images are evaluated for general features, edge maps, and regions of interest, using a method based on Watershedding K-Means segments. We propose an image recovery process that relies on a new similarity measure between all feature descriptions. New trademark images are added every day to ensure up-to-date results. The proposed system showcases a timely retrieval speed, with 95% of searches having a 10 second presentation speed and a mean average precision of 93.7%, supporting its applicability to real-word IP protection scenarios.

Imaging faint sources with the extended solar gravitational lens

We consider resolved imaging of faint sources with the solar gravitational lens (SGL) while treating the Sun as an extended gravitating body. We use our new diffraction integral that describes how a spherical electromagnetic wave is modified by the static gravitational field of an extended body, represented by series of multipole moments characterizing its interior mass distribution. Dominated by the solar quadrupole moment, these deviations from spherical symmetry significantly perturb the image that is projected by the Sun into its focal region, especially at solar equatorial latitudes. To study the optical properties of the quadrupole SGL, we develop an approximate solution for the point spread function of such an extended lens. We also derive semianalytical expressions to estimate signal levels from extended targets. With these tools, we study the impact of solar oblateness on imaging with the SGL. Given the small value of the solar quadrupole moment, the majority of the signal photons arriving from an extended target still appear within the image area projected by the monopole lens. However, these photons are scrambled, thus reducing the achievable signal-to-noise ratio during the image recovery process (i.e., deconvolution). We also evaluate the spectral sensitivity for high-resolution remote sensing of exoplanets with the extended SGL. We assess the impact on image quality and demonstrate that despite the adverse effects of the quadrupole moment, the SGL remains uniquely capable of delivering high-resolution imaging and spectroscopy of faint, small, and distant targets, notably terrestrial exoplanets within $\ensuremath{\sim}30--100\text{ }\text{ }\mathrm{parsec}$ from us.

Photon-limited Cherenkov imaging of radiation therapy dose.

Cherenkov imaging is a unique verification tool that could provide both dosimetric and tissue functional information during radiation therapy. However, the number of interrogated Cherenkov photons in tissue is always limited and tangled with stray radiation photons, severely frustrating the measurement the signal-to-noise ratio (SNR). As such, here, a noise-robust photon-limited imaging technique is proposed by comprehensively exploiting the physical rationale of low-flux Cherenkov measurements together with the spatial correlations of the objects. Validation experiments confirmed that the Cherenkov signal could be promisingly recovered with high SNR by irradiating at as few as one x ray pulse from a linear accelerator (10 mGy dose), and the Cherenkov excited luminescence imaging depth can be extended by >100% on average, for most concentrations of phosphorescent probe. This approach demonstrates that improved applications in radiation oncology could be seen when signal amplitude, noise robustness, and temporal resolution are comprehensively considered in the image recovery process.

Fourier Ptychography Reconstruction Based on Reweighted Amplitude Flow With Regularization by Denoising and Deep Decoder

Fourier ptychography (FP) is a computational imaging technique with the advantage that it can obtain large field-of-view (FOV) and high-resolution (HR) imaging. We propose an algorithm for Fourier ptychography based on reweighted amplitude flow (RAF) with regularization by denoising (RED) and deep decoder (DD), which is an untrained deep generative model. The proposed method includes two loops, using reweighted amplitude flow with regularization by denoising as an inner loop for phase retrieval and deep decoder for further denoising as an outer loop in the Fourier ptychography recovery system. The proposed method does not need any training dataset, just adds a little computer time during the image recovery process. The proposed method has no bias due to training images, which is different from other deep learning methods. The experimental results show that the proposed method can improve the reconstruction quality in both PSNR and SSIM.

Target Imaging Using Compressed Sampling in Synthetic Aperture Interferometric Radiometer

The target imaging application is significant to various sensing systems, such as radiometers, radars, and infrared. However, high system complexity impedes the application of interferometric radiometers to target imaging tasks to some extent. Specifically for an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> -element interferometric radiometer with aperture synthesis technique, complex correlators are of the order of O( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ), giving rise to the great difficulty of system hardware implementation. In this paper, we propose a new compressed interferometric radiometer (CIR) concept for target imaging applications, which exploits the sparsity property of targets in the spatial domain. The CIR target imaging framework mainly adopts the compressive measurement method to acquire partial visibility function samples in the spatial-frequency domain via a proper sparse sampling pattern. Then, these partially observed visibility samples are inverted to image the target contrast information by sparse recovery methods. For the above image recovery process, we propose two novel algorithms named local regional information-based reweighted <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</i> 1-norm minimization (LRRL1) and local regional convolution-based reweighted <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</i> 1-norm minimization (LRCRL1). The experiments using simulated and real data demonstrate the validity and effectiveness of the proposed CIR target imaging framework, showing superiority in both imaging performance and system complexity compared with conventional algorithms used in interferometric radiometers.

Structures Guided Dynamic Scene Deblurring Method

In this paper, we integrate image gradient priors into a generative adversarial networks (GANs) to deal with the dynamic scene deblurring task. Even though image deblurring has progressed significantly, the deep learning-based methods rarely take advantage of image gradients priors. Image gradient priors regularize the image recovery process and serve as a quantitative evaluation metric for evaluating the quality of deblurred images. In contrast to previous methods, the proposed model utilizes a data-driven way to learn image gradients. Under the guidance of image gradient priors, we permeate it throughout the design of network structures and target loss functions. For the network architecture, we develop a GradientNet to compute image gradients via horizontal and vertical directions in parallel rather than adopt traditional edge detection operators. For the loss functions, we propose target loss functions to constrain the network training. The proposed image deblurring strategy discards the tedious steps of solving optimization equations and taking further advantage of learning massive data features through deep learning. Extensive experiments on synthetic datasets and real-world images demonstrate that our model outperforms state-of-the-art (SOAT) methods.

Image Deblurring Algorithm Based on the Gaussian-Scale Mixture Expert Field Model

With the proliferation of portable digital products, image quality degradation has received a lot of attention. As the most common phenomenon in image degradation, the issue of image deblurring is the focus of much attention. Blind motion blur removal is the main target of this paper. The heavy-tailed distribution is the most dominant statistical feature of natural images. However, most image deblurring methods use a gradient prior with fixed parameters to recover a clear image, which leads to loss of details in the recovered clear image and does not consider the higher order prior of the natural image. Therefore, this paper proposes a new regularized image recovery model based on the Gaussian-scale mixture expert field(GSM-FOE) model. First, the GSM-FoE model learns filters and corresponding parameters with higher order prior information of images by training images in a natural image library; second, these learning results are used to guide the image recovery process. The GSM-FoE model and gradient-fidelity based image recovery model is proposed, which can be used with an iterative re-weighted least squares (IRLS) method. Experiments demonstrate that the suggested recovery approach is simple to use and successful at reducing blur and noise, as well as suppressing ringing effects while preserving image information. Moreover, the image restoration method performs well for large blurring kernels. The results fully reflect the effectiveness and robustness of the proposed method for complex noise scenarios. The quality of the generated images is significantly better than that of several classical methods.

Two-Stage CNN Model for Joint Demosaicing and Denoising of Burst Bayer Images.

In the classical image processing pipeline, demosaicing and denoising are separated steps that may interfere with each other. Joint demosaicing and denoising utilizes the shared image prior information to guide the image recovery process. It is expected to have better performance by the joint optimization of the two problems. Besides, learning recovered images from burst (continuous exposure images) can further improve image details. This article proposes a two-stage convolutional neural network model for joint demosaicing and denoising of burst Bayer images. The proposed CNN model consists of a single-frame joint demosaicing and denoising module, a multiframe denoising module, and an optional noise estimation module. It requires a two-stage training scheme to ensure that the model converges to a good solution. Experiments on multiframe Bayer images with simulated Gaussian noise show that the proposed method has obvious performance advantages and speed advantages compared with similar approaches. Experiments on actual multiframe Bayer images verify the denoising effect and detail retention ability of the proposed method.

Lossless progressive secret sharing for grayscale and color images

A new technique on progressive secret sharing is presented. The proposed method offers two different approaches on converting a secret image into a set of shared images. The first approach exploits the generalized random grids or bitwise level computation, whereas the second approach utilizes the eXclusive-OR (XOR) operation to generate a set of shared images. The proposed method has lossless ability in the recovery process of secret image. This scheme performs well not only for binary image, but it also gives satisfactory result for grayscale and color secret image. As results show that the proposed method yields better results compared to the former existing schemes under visual investigation and objective assessment on the recovered secret image. In addition, the proposed method does not require high computational burden in the shared image generation as well as in the secret image recovery process. Yet, it can be regarded as good candidate for applying the progressive secret sharing with lossless reconstruction constraint.

ADMM based low-rank and sparse matrix recovery method for sparse photoacoustic microscopy

Photoacoustic microscopy (PAM) has evolved into a new promising medical imaging tool available for both in vivo surficial and deep-tissue imaging with a high spatial resolution. However, the long data acquisition time has made real-time imaging highly challenging. This paper presents an Alternating Direction Method of Multipliers (ADMM) based low-rank and sparse matrix recovery method for a sparse optical-scanning PAM system to realize fast PAM vascular imaging.For our system, an x-y galvanometer scanner is used to achieve compressive sampling, and the associated image recovery process is formulated as a matrix completion problem. The sparse scanning scheme might be easy to integrate with several other optical-resolution PAM modalities. Further, the sparse constraint (the total variation norm) and the low-rank constraint (nuclear norm) are combined for solving the optimization program under ADMM framework for matrix recovery in order to achieve better PAM image recovery even for images that are not well-approximated by their low-rank components.A prototype PAM system has been implemented and the recovery method has been validated. From both visual effects and quantitative parameters, such as PSNR, SSIM, Rerr and MSE, comparable image qualities with conventional full sampling optical resolution PAM could be acquired by just half of the data acquisition time. Besides, the ADMM based low-rank and sparse matrix recovery method could show better results than GoDec. The obtained results demonstrate the preclinical and clinical potential of sparse PAM system in investigating vascular diseases.

Deep D-Bar: Real-Time Electrical Impedance Tomography Imaging With Deep Neural Networks.

The mathematical problem for electrical impedance tomography (EIT) is a highly nonlinear ill-posed inverse problem requiring carefully designed reconstruction procedures to ensure reliable image generation. D-bar methods are based on a rigorous mathematical analysis and provide robust direct reconstructions by using a low-pass filtering of the associated nonlinear Fourier data. Similarly to low-pass filtering of linear Fourier data, only using low frequencies in the image recovery process results in blurred images lacking sharp features, such as clear organ boundaries. Convolutional neural networks provide a powerful framework for post-processing such convolved direct reconstructions. In this paper, we demonstrate that these CNN techniques lead to sharp and reliable reconstructions even for the highly nonlinear inverse problem of EIT. The network is trained on data sets of simulated examples and then applied to experimental data without the need to perform an additional transfer training. Results for absolute EIT images are presented using experimental EIT data from the ACT4 and KIT4 EIT systems.

Reversible Data Hiding Scheme During Encryption Using Machine Learning

Reversible data hiding (RDH) is a recent research field of information security for secured digital data transmission. The advancements in communication technology and the invention of new medical robotics are very much useful in telemedicine applications. The transmission of medical image and electronic patient records (EPR) is a common process in telemedicine. The images captured by robots may need to be authenticated, the RDH schemes can be used to authenticate data and/or the owner of the data. In addition, the RDH techniques provide a way to embed EPR data into medical images before transmission. The EPR data extraction and recovery of the original image can be carried out by the receiver. This manuscript proposes a new RDH scheme to embed EPR data during image encryption process. A block-wise image encryption technique has been used in the proposed scheme to obtain the encrypted image with hidden EPR data bits. The novelty of the proposed scheme is that a support vector machine (SVM) based classification scheme has been used for data extraction and image recovery process from the encrypted image. Experimental study of the proposed scheme on standard medical images from OsriX dataset shows that the proposed scheme performs better than the existing schemes in terms of embedding rate and bit error rate.

Compressive multi-spectral imaging using self-correlations of images based on hierarchical joint sparsity models

We propose a novel multi-spectral imaging method based on compressive sensing (CS). In CS theory, the enhancement of signal sparsity is important for accurate signal reconstruction. The main novelty of the proposed method is the employment of a self-correlation of an image, that is a local intensity similarity and multi-spectral correlation, to enhance the sparsity of the multi-spectral image to be recovered. Local intensity similarity, which is based on the concept that spatial changes in intensity are likely to be similar within local regions, contributes to sparsity enhancement. Furthermore, we exploit multi-spectral correlation to improve the sparsity of the multi-spectral components to be recovered. In order to simultaneously exploit different types of characteristics (i.e., local intensity similarity and multi-spectral correlation) for representing a signal as sufficiently sparse, we introduce a hierarchical joint sparsity model in the CS image recovery process. Our experiments show that the use of a self-correlation significantly improves the performance of multi-spectral image reconstruction.

Compressed sensing magnetic resonance imaging based on dictionary updating and block‐matching and three‐dimensional filtering regularisation

Compressed sensing (CS) enables that magnetic resonance (MR) images can be exactly reconstructed from undersampled k-space data by exploiting the sparsity of MR images in some analytical sparsifying transform or some dictionary. Recent methods are exploiting adaptive patch-based dictionaries for image recovery by alternating between dictionary learning step and image reconstruction step. In this study, the authors propose a novel MR image reconstruction algorithm utilising dictionary updating, which consists of three steps: sparse coding, dictionary updating and image reconstruction. In the dictionary updating step, they perform a first-order series expansion for dictionary–coefficient matrix product via recursive method, and propose an efficient method to solve the new dictionary updating problem. To improve the reconstruction quality, the proposed block-matching and three-dimensional (3D) filtering regularisation is incorporated into the authors’ image CS recovery, which can combine the self-similarities within the image, the 3D transform sparsity and the local sparsity into image recovery process. Experimental simulations demonstrate their proposed algorithms can obtain better reconstruction quality than the previous CS algorithms.

Super-Resolution Reconstruction of Diffusion-Weighted Images using 4D Low-Rank and Total Variation

Diffusion-weighted imaging (DWI) provides invaluable information in white matter microstructure and is widely applied in neurological applications. However, DWI is largely limited by its relatively low spatial resolution. In this paper, we propose an image post-processing method, referred to as super-resolution reconstruction, to estimate a high spatial resolution DWI from the input low-resolution DWI, e.g., at a factor of 2. Instead of requiring specially designed DWI acquisition of multiple shifted or orthogonal scans, our method needs only a single DWI scan. To do that, we propose to model both the blurring and downsampling effects in the image degradation process where the low-resolution image is observed from the latent high-resolution image, and recover the latent high-resolution image with the help of two regularizations. The first regularization is 4-dimensional (4D) low-rank, proposed to gather self-similarity information from both the spatial domain and the diffusion domain of 4D DWI. The second regularization is total variation, proposed to depress noise and preserve local structures such as edges in the image recovery process. Extensive experiments were performed on 20 subjects, and results show that the proposed method is able to recover the fine details of white matter structures, and outperform other approaches such as interpolation methods, non-local means based upsampling, and total variation based upsampling.

Time-stretch high-speed microscopic imaging system based on temporally and spectrally shaped amplified spontaneous emission.

In this Letter, a time-stretch high-speed microscopic imaging system based on temporally and spectrally shaped amplified spontaneous emission (ASE) is proposed and experimentally demonstrated. We significantly reduced the complexity and cost of the light source by applying ASE in the time-stretch microscopic imaging system. Furthermore, by slicing and preprocessing the spectrum of the ASE with a Fabry-Perot (F-P) filter, the random intensity vibration of the ASE can be significantly suppressed, which would notably simplify the image recovery process afterward. The resolution of the proposed system is better than 35μm and the effective 1D scan rate could reach 50MHz.

Analysis of Secret Image Sharing using Shared Image

secret image sharing scheme with steganography lacks to provide the authentication, quality of stego-image and more cheating done by the dishonest participants. So, a secret image sharing using shared image technique is proposed to prevent the participants from the subsidiary stipulation of a false stego-image (an image containing the hidden secret image). A secret image is first processed into n shares which are then hidden in n user-selected suppression images. It is recommended to select these suppression images to contain well-known stuffing to increase the steganographic effect for the security protection. Additionally, an image watermarking technique is engaged to embed fragile watermark signals into the suppression images by the use of parity-bit checking, thus providing the ability of authenticating the reliability of each processed suppression image. During the secret image recovery process, each stego- image carry by a participant is first verified for its reliability by checking the uniformity of the parity conditions found in the image pixels. This facilitates to avert the participant from subsidiary stipulation of a false stego-image. Some effective techniques for handling large images as well as for enhancing security protection are employed. As a result, the secret image sharing using shared image scheme offers a high secure and effective mechanism for secret image sharing that is not found in existing secret image sharing methods. High-class experimental results proving the authentication capability, secret hiding effectiveness and quality of the proposed approach are included. Keywordsecret image sharing, Steganography, Authentication, suppression image, Data hiding, Stego-image, Fragile watermarking.

Speckle suppression via sparse representation for wide-field imaging through turbid media.

Speckle suppression is one of the most important tasks in the image transmission through turbid media. Insufficient speckle suppression requires an additional procedure such as temporal ensemble averaging over multiple exposures. In this paper, we consider the image recovery process based on the so-called transmission matrix (TM) of turbid media for the image transmission through the media. We show that the speckle left unremoved in the TM-based image recovery can be suppressed effectively via sparse representation (SR). SR is a relatively new signal reconstruction framework which works well even for ill-conditioned problems. This is the first study to show the benefit of using the SR as compared to the phase conjugation (PC) a de facto standard method to date for TM-based imaging through turbid media including a live cell through tissue slice.

Reversible data hiding scheme based on exploiting modification direction with two steganographic images

In this paper, we propose a novel data hiding scheme with reversibility based on exploiting modification direction (EMD). One cover image is first chosen and prepared to generate two visually similar steganographic images. During the secret embedding, the pixels in the first steganographic image are modified by no more than one gray level to embed secret data using the traditional EMD method, while the pixels in the second steganographic image are adaptively modified through referring to the first steganographic image without any confusions in image recovery process. On the receiver side, secret data can be extracted easily and the original cover image can also be recovered from the two steganographic images correctly. Experimental results demonstrate that our scheme can achieve high hiding capacity and satisfactory visual quality.

A Novel Approach on Color Image Refocusing and Defocusing

In this study we present a novel approach on a color image refocusing and defocusing. In detail, the proposed method can accomplish the tasks of color image refocusing and defocusing. Our proposed method is thus a process of recovering the original color image from the degraded color image observations. This approach has the advantage of canny edge detection process for preserving the sharp Edges and lines of color images for restoring the blurred color image. Blind deconvolution algorithm is used to blurred images where image recovery process has been performed with little or no prior knowledge of the degrading point spread function.