Sparse Image Research Articles

ICe: interior cevian initialization for enhanced reconstruction methods

This paper introduces two novel self-induced basis strategies, interior cevian initialization for orthogonal matching pursuit (ICe) and its l2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l_2$$\\end{document}-sense optimized version, optimized interior cevian initialization (OICe). These methods address the complexity and convergence issues of the previously proposed self-inspired bases (SIBS) approach. Both algorithms enhance sparse image representation by generating adaptive auxiliary atoms tailored to the image, thereby improving reconstruction quality and computational efficiency. Experimental results show that ICe achieves up to a 35.6% improvement in Normalized Mean Squared Error (NMSE) and a 16.4% increase in Structural Similarity Index (SSIM) compared to conventional OMP. OICe, as the l2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l_2$$\\end{document}-sense optimized version of ICe, delivers even greater performance, with improvements of up to 40% in NMSE and 18.5% in SSIM. Additionally, both ICe and OICe significantly reduce bits per pixel (BPP) for image encoding, outperforming SIBS when paired with state-of-the-art dictionaries such as KSVD, MOD, RBDL, and ODL. These results highlight the effectiveness of ICe and OICe in addressing key challenges in sparse representation, offering enhanced accuracy and efficiency across a variety of applications.

Hybrid plug-and-play CT image restoration using nonconvex low-rank group sparsity and deep denoiser priors

Abstract Objective. Low-dose computed tomography (LDCT) is an imaging technique that can effectively help patients reduce radiation dose, which has attracted increasing interest from researchers in the field of medical imaging. Nevertheless, LDCT imaging is often affected by a large amount of noise, making it difficult to clearly display subtle abnormalities or lesions.
Therefore, this paper proposes a multiple complementary priors CT image reconstruction method by simultaneously considering both the internal prior and external image information of CT images, thereby enhancing the reconstruction quality of CT images.
Approach. Specifically, we propose a CT image reconstruction method based on weighted nonconvex low-rank regularized group sparse and deep image priors under hybrid plug-and-play framework by utilizing the weighted nonconvex low rankness and group sparsity of dictionary domain coefficients of each group of similar patches, and a convolutional neural network (CNN) denoiser.
To make the proposed reconstruction problem easier to tackle, we utilize the Alternate Direction Method of Multipliers (ADMM) for optimization.Main results. To verify the performance of the proposed method, we conduct detailed simulation experiments on the images of the abdominal, pelvic, and thoracic at projection views of 45, 65, and 85, and at noise levels of 1×10^5 and 1×10^6, respectively. A large number of qualitative and quantitative experimental results indicate that the proposed method has achieved better results in texture preservation and noise suppression compared to several existing iterative reconstruction methods.
Significance. The proposed method fully considers the internal nonlocal low rankness and sparsity, as well as the external local information of CT images, providing a more effective solution for CT image reconstruction. Consequently, this method enables doctors to diagnose and treat diseases more accurately by reconstructing high-quality CT images.

H3T: Hierarchical Transferable Transformer with TokenMix for Unsupervised Domain Adaptation

Recent research has been focused on exploring the capabilities of Vision Transformers (ViTs) in Unsupervised Domain Adaptation (UDA). This approach typically involves providing more significant attention to fine-grained common information through patch-level transferable discrimination. However, prematurely assigning narrow-range transferability information at the encoding stage can sparse image information, thereby increasing the difficulty of downstream tasks. Therefore, we propose a Hierarchical Transferable Transformer with TokenMix (H3T), which maintains the allocation of fine-grained transferability at the encoding stage while enhancing the learning strength of image information through feature mixup. To address the challenge of missing sample labels in the target domain within the domain adaptation task, we have specifically designed the TokenMix Module (TMM) for ViTs. This module learns the style information from both domains while alleviating the impact of image sparsity on downstream tasks. Furthermore, to enhance the semantic connections among narrow-range image transfer messages, we propose the Hierarchical Discriminative Module (HDM), which also serves a critical role in encoding discriminative information. Our approach underwent comprehensive experimentation across five datasets of varying sizes, demonstrating its effectiveness. Our code is available at https://github.com/reyihua/H3T.

Secure authentication and encryption via diffraction imaging-based encoding and vector decomposition

Abstract Traditional optical encryption systems have security risks due to their linearity and usually encounter problems such as the heavy burden of key transmission and storage. This paper proposes a novel security-enhanced optical image authentication and encryption framework that combines diffractive imaging-based encryption with the vector decomposition algorithm (VDA). Chaotic random phase masks (CRPMs) are used to encrypt data for authentication via VDA, and a pair of complementary binary matrix keys are utilized to extract information from the encrypted data to generate ciphertext. During the authentication and decryption processes, a sparse reference image is reconstructed from the ciphertext for verification. If the authentication is successful, image decryption can be executed using a key-assisted phase retrieval algorithm. The employment of nonlinear VDA, an additional layer of authentication, and the use of CRPMs and binary matrix keys enhance security and address key burden concerns. Simulation results demonstrate the feasibility, effectiveness, and security of the scheme.

Real-time four-dimensional scanning transmission electron microscopy through sparse sampling

Abstract Four-dimensional scanning transmission electron microscopy (4-D STEM) is a state-of-theart image acquisition mode used to reveal high and low mass elements at atomic resolution. The acquisition of the electron momenta at each real space probe location allows for various analyses to be performed from a single dataset, including virtual imaging, electric field analysis, as well as analytical or iterative extraction of the object induced phase shift. However, the limiting factor in 4-D STEM is the speed of acquisition which is bottlenecked by the read-out speed of the camera, which must capture a convergent beam electron diffraction (CBED) pattern at each probe position in the scan. Recent developments in sparse sampling and image inpainting (a branch of compressive sensing) for STEM have allowed for real-time recovery of sparsely acquired data from fixed monolithic detectors, Further developments in compressive sensing for 4-D STEM have also demonstrated that acquisition speeds can be increased i.e. live video rate 4D imaging is now possible. In this work, we demonstrate the first practical implementations of compressive 4-D STEM for real-time inference on two different scanning transmission electron microscopes.

An adaptive parameter decoupling algorithm-based image reconstruction model (ADAIR) for rapid golden-angle radial DCE-MRI

Objective. The acceleration of magnetic resonance imaging (MRI) acquisition is crucial for both clinical and research applications, particularly in dynamic MRI. Existing compressed sensing (CS) methods, despite being effective for fast imaging, face limitations such as the need for incoherent sampling and residual noise, which restrict their practical use for rapid MRI.Approach. To overcome these challenges, we propose a novel image reconstruction framework that integrates the MRI physical model with a flexible, self-adjusting, decoupling data-driven model. We validated this method through experiments using both simulated andin vivodynamic contrast-enhanced MRI datasets.Main results. The experimental results demonstrate that the proposed framework achieves high spatial and temporal resolution reconstructions. Additionally, when compared to state-of-the-art image reconstruction approaches, our method significantly enhances acceleration capabilities, enabling sparse and rapid imaging with high resolution.Significance. Our proposed framework offers a promising solution for real-time imaging and image-guided radiation therapy applications by providing superior performance in achieving high spatial and temporal resolution reconstructions, thus addressing the limitations of existing CS schemes.

Deep Learning-Based Approximated Observation Sparse SAR Imaging via Complex-Valued Convolutional Neural Network

Sparse synthetic aperture radar (SAR) imaging has demonstrated excellent potential in image quality improvement and data compression. However, conventional observation matrix-based methods suffer from high computational overhead, which is hard to use for real data processing. The approximated observation sparse SAR imaging method relieves the computation pressure, but it needs to manually set the parameters to solve the optimization problem. Thus, several deep learning (DL) SAR imaging methods have been used for scene recovery, but many of them employ dual-path networks. To better leverage the complex-valued characteristics of echo data, in this paper, we present a novel complex-valued convolutional neural network (CNN)-based approximated observation sparse SAR imaging method, which is a single-path DL network. Firstly, we present the approximated observation-based model via the chirp-scaling algorithm (CSA). Next, we map the process of the iterative soft thresholding (IST) algorithm into the deep network form, and design the symmetric complex-valued CNN block to achieve the sparse recovery of large-scale scenes. In comparison to matched filtering (MF), the approximated observation sparse imaging method, and the existing DL SAR imaging methods, our complex-valued network model shows excellent performance in image quality improvement especially when the used data are down-sampled.

A Comprehensive Analysis of Traditional and Advanced Approaches of Image Restoration Techniques

Introduction: Tremendous developments in multimedia technology have promoted a massive amount of research in image and video processing. As imaging technologies are rapidly increasing, it is becoming essential to use images in almost every application in our day-today life. Materials and Method: This paper presents a comparative analysis of various image restoration approaches, ranging from fundamental methods to advanced techniques. These approaches aim to improve the quality of images that have been degraded during acquisition or transmission. A brief overview of the image restoration approaches is mentioned in the paper, which are as follows: Wiener Filter: The Wiener filter is a classical approach used for image restoration. It is a linear filter that minimizes the mean square error between the original image and the restored image. Inverse Filter: The inverse filter is another traditional restoration technique. It attempts to invert the degradation process to recover the original image. However, inverse filtering is highly sensitive to noise and tends to amplify noise artifacts. Linear and Nonlinear Filtering: These methods involve applying linear or nonlinear filters to the degraded image to enhance its quality. Linear filters, such as Gaussian filters, can effectively reduce noise but may blur the image. Nonlinear filters, such as median filters, can preserve edges while reducing noise. Compressive Sensing (CS) Restoration Approaches: Compressive sensing is a signal processing technique that exploits the sparsity of signals or images to reconstruct them from fewer measurements. CS-based restoration methods aim to recover high-quality images from compressed or incomplete measurements. Neural Networks Approaches: With the advancements in deep learning, neural networks have been widely used for image restoration tasks. Convolutional neural networks (CNNs) and generative adversarial networks (GANs) have shown promising results in restoring degraded images by learning from large datasets. Result: The paper likely provides a detailed analysis and comparison of these approaches, highlighting their strengths, weaknesses, and performance in different scenarios. Conclusion: This paper aims to improve the quality of restored images. Several image restoration approaches have been compared, and they have exhibited enhanced performance compared to several existing image restoration approaches.

Dynamic sparse x-ray nanotomography reveals ionomer hydration mechanism in polymer electrolyte fuel-cell catalyst.

Tomographic imaging of time-evolving samples is a challenging yet important task for various research fields. At the nanoscale, current approaches face limitations of measurement speed or resolution due to lengthy acquisitions. We developed a dynamic nanotomography technique based on sparse dynamic imaging and 4D tomography modeling. We demonstrated the technique, using ptychographic x-ray computed tomography as its imaging modality, on resolving the in situ hydration process of polymer electrolyte fuel cell (PEFC) catalyst. The technique provides a 40-time increase in temporal resolution compared to conventional approaches, yielding 28 nm half-period spatial and 12 min temporal resolution. The results allow a quantitative characterization of the water intake process inside PEFC catalysts with nanoscale resolution, which is crucial for understanding their electrochemical mechanisms and optimizing their performance. Our technique enables high-speed operando nanotomography studies and paves the way for wider application of dynamic tomography at the nanoscale.

Mid-frequency contrast compensation for sparse aperture imaging systems by increasing the size of a sub-aperture

Mid-frequency contrast compensation for sparse aperture imaging systems by increasing the size of a sub-aperture

A new proximal gradient method for solving mixed variational inequality problems with a novel explicit stepsize and applications

In this paper, we propose a new algorithm for solving monotone mixed variational inequality problems in real Hilbert spaces based on proximal gradient method. Our new algorithm uses a novel explicit stepsize which is proved to be increasing to a positive limitation. This property plays an important role in improving the speed of the algorithm. To the best of our knowledge, it is the first time such a kind of stepsize has been proposed for the proximal gradient method solving mixed variational inequality problems. We prove the weak convergence and strong convergence with R-linear rate of our new algorithm under standard assumptions. The reported numerical simulations for applications in sparse logistic regression and image deblurring reveal the significant efficacy performance of our proposed method compared to the recent ones.

Intelligent fatigue damage tracking and prognostics of composite structures utilizing raw images via interpretable deep learning

In recent years, prognostics gained attention in various industries by optimizing maintenance, boosting operational efficiency, and preventing costly downtime. Central to prognostics is the Remaining Useful Life (RUL), representing the critical time before system failure. Deep learning advancements facilitate RUL forecasting by extracting features from diverse data formats such as time series, images, or sequences thereof, in one, two, or three dimensions, respectively. Yet, predicting RUL from image sequences often relies heavily on resource-intensive techniques like digital image correlation, complicating data acquisition. To address challenges with high-dimensional data and unreliable models, this study introduces ISTRUST, an innovative Transformer-based architecture. ISTRUST (Interpretable Spatiotemporal TRansformer for Understanding STructures) tackles the dual challenges posed by high-dimensional data and the black-box nature of existing models. Leveraging Transformers’ attention mechanism, ISTRUST breaks down the spatiotemporal domain, effectively realizing interpretable RUL predictions under uncertainty using only sparse raw image sequences as input. Evaluated on fatigue-loaded composite samples showcasing crack propagation, ISTRUST interprets the relation between cracks and RUL via the attention mechanism. The results substantiate its capacity to interpret and clarify instances in which predictions may exhibit variability in accuracy. Through the attention mechanism, a strong correlation between the model’s spatiotemporal focus and the RUL predictions is established, making it, to the best of our knowledge, the first model to provide interpretable stochastic RUL predictions directly from sequential images of this nature.

An accelerated alternating direction method of multiplier for MRI with TV regularisation

Compressed Sensing (CS) is important in the field of image processing and signal processing, and CS-Magnetic Resonance Imaging (MRI) is used to reconstruct image from undersampled k-space data. Total Variation (TV) regularisation is a common technique to improve the sparsity of image, and the Alternating Direction Multiplier Method (ADMM) plays a key role in the variational image processing problem. This paper aims to improve the quality of MRI and shorten the reconstruction time. We consider MRI to solve a linear inverse problem, we convert it into a constrained optimization problem based on TV regularisation, then an accelerated ADMM is established. Through a series of theoretical derivations, we verify that the algorithm satisfies the convergence rate of O1/k2 under the condition that one objective function is quadratically convex and the other is strongly convex. We select five undersampled templates for testing in MRI experiment and compare it with other algorithms, experimental results show that our proposed method not only improves the running speed but also gives better reconstruction results.

Self-supervised learning on MeerKAT wide-field continuum images

Context. Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in models that are adaptable to many different tasks. Until now, applications of SSL to astronomical images have been limited to Galaxy Zoo datasets, which require a significant amount of preprocessing to prepare sparse images centered on a single galaxy. With wide-field survey instruments at the forefront of the Square Kilometer Array (SKA) era, this approach to gathering training data is impractical. Aims. We demonstrate that continuum images from surveys such as the MeerKAT Galactic Cluster Legacy Survey (MGCLS) can be successfully used with SSL, without extracting single-galaxy cutouts. Methods. Using the SSL framework DINO, we experimented with various preprocessing steps, augmentations, and architectures to determine the optimal approach for this data. We trained both ResNet50 and Vision Transformer (ViT) backbones. Results. Our models match state-of-the-art results (trained on Radio Galaxy Zoo) for FRI/FRII morphology classification. Furthermore, they predict the number of compact sources via linear regression with much higher accuracy. Open-source foundation models trained on natural images such as DINOv2 also excel at simple FRI/FRII classification; the advantage of domain-specific backbones is much smaller models trained on far less data. Smaller models are more efficient to fine-tune, and doing so results in a similar performance between our models, the state-of-the-art, and open-source models on multi-class morphology classification. Conclusions. Using source-rich crops from wide-field images to train multi-purpose models is an easily scalable approach that significantly reduces data preparation time. For the tasks evaluated in this work, twenty thousand crops is sufficient training data for models that produce results similar to state-of-the-art. In the future, complex tasks like source detection and characterization, together with domain-specific tasks, ought to demonstrate the true advantages of training models with radio astronomy data over natural-image foundation models.

Information sparsity guided transformer for multi-modal medical image super-resolution

Multi-modal medical image super-resolution (SR) plays a vital role in enhancing the resolution of medical images, providing more detailed visuals that aid in accurate clinical diagnosis. Recently, Transformer-based super-resolution methods have significantly promoted performance improvement in this field due to their capacity to capture global dependencies. They usually process all non-overlapping patches as tokens and densely sample these tokens without screening for calculating attention mechanisms. However, this strategy ignores the spatial sparsity of medical images, resulting in redundant or even detrimental computations on less informative regions. Hence, this paper proposes a novel sparsity-guided medical image SR network, namely SG-SRNet, by exploiting the spatial sparsity characteristics of the medical images. SG-SRNet mainly consists of two components: a sparsity mask (SM) generator for image sparsity estimation, and a sparsity-guided Transformer (SGTrans) for high-resolution image reconstruction. Specially, the SM generator generates a sparsity mask by minimizing our cross-sparsity loss which can respond to the informative positions. SGTrans first screens out the informative patches according to the sparsity mask. Then, SGTrans utilizes the designed cluster-based attention to only calculate attention between information-related tokens. We perform comprehensive experiments on three datasets to show that SG-SRNet brings significant performance enhancements with low computational complexity.

Optimization of Sparse Camera Array Arrangement using Grid-based Method

—This study explores the application of multi-camera array technology in super-resolution (SR) imaging system. We propose an innovative method based on grid representation to optimize camera arrangements using sparse Gaussian processes and variational inference. This approach significantly enhances the image reconstruction quality of sparse camera arrays. Unlike conventional techniques that provide only qualitative conclusions, our grid-based method precisely optimizes camera positions and effectively simulates the impact of assembly errors. The optimized camera arrangement substantially improves the SR reconstruction quality of sparse array imaging systems, reducing contour jaggedness and high-frequency aliasing. Extensive simulations and experimental validations confirm the robustness and practical applicability of our method. The results demonstrate that the optimized camera arrangements can achieve high-resolution imaging with enhanced robustness against assembly errors, indicating their potential for various applications such as biological microscopy, remote sensing, and smartphone photography. This work presents a new and effective strategy for designing sparse camera array imaging systems, offering significant improvements in both image quality and system reliability.

Rapid Hyperspectral Photothermal Mid-Infrared Spectroscopic Imaging from Sparse Data for Gynecologic Cancer Tissue Subtyping.

Ovarian cancer detection has traditionally relied on a multistep process that includes biopsy, tissue staining, and morphological analysis by experienced pathologists. While widely practiced, this conventional approach suffers from several drawbacks: it is qualitative, time-intensive, and heavily dependent on the quality of staining. Mid-infrared (MIR) hyperspectral photothermal imaging is a label-free, biochemically quantitative technology that, when combined with machine learning algorithms, can eliminate the need for staining and provide quantitative results comparable to traditional histology. However, this technology is slow. This work presents a novel approach to MIR photothermal imaging that enhances its speed by an order of magnitude. This method resolves the longstanding trade-off between imaging resolution and data collection speed, enabling the reconstruction of high-quality, high-resolution images from undersampled data sets and achieving a 10X improvement in data acquisition time. We assessed the performance of our sparse imaging methodology using a variety of quantitative metrics, including mean squared error (MSE), structural similarity index (SSIM), and tissue subtype classification accuracies, employing both random forest and convolutional neural network (CNN) models, accompanied by Receiver Operating Characteristic (ROC) curves. Our statistically robust analysis, based on data from 100 ovarian cancer patient samples and over 65 million data points, demonstrates the method's capability to produce superior image quality and accurately distinguish between different gynecological tissue types with segmentation accuracy exceeding 95%. Our work demonstrates the feasibility of integrating rapid MIR hyperspectral photothermal imaging with machine learning in enhancing ovarian cancer tissue characterization, paving the way for quantitative, label-free, automated histopathology.

The Adaption of Recent New Concepts in Neural Radiance Fields and Their Role for High-Fidelity Volume Reconstruction in Medical Images.

Volume reconstruction techniques are gaining increasing interest in medical domains due to their potential to learn complex 3D structural information from sparse 2D images. Recently, neural radiance fields (NeRF), which implicitly model continuous radiance fields based on multi-layer perceptrons to enable volume reconstruction of objects at arbitrary resolution, have gained traction in natural image volume reconstruction. However, the direct application of NeRF to medical volume reconstruction presents unique challenges due to differences in imaging principles, internal structure requirements, and boundary delineation. In this paper, we evaluate different NeRF techniques developed for natural images, including sampling strategies, feature encoding, and the use of complimentary features, by applying them to medical images. We evaluate three state-of-the-art NeRF techniques on four datasets of medical images of different complexity. Our goal is to identify the strengths, limitations, and future directions for integrating NeRF into the medical domain.

Joint segmentation and image reconstruction with error prediction in photoacoustic imaging using deep learning

Deep learning has been used to improve photoacoustic (PA) image reconstruction. One major challenge is that errors cannot be quantified to validate predictions when ground truth is unknown. Validation is key to quantitative applications, especially using limited-bandwidth ultrasonic linear detector arrays. Here, we propose a hybrid Bayesian convolutional neural network (Hybrid-BCNN) to jointly predict PA image and segmentation with error (uncertainty) predictions. Each output pixel represents a probability distribution where error can be quantified. The Hybrid-BCNN was trained with simulated PA data and applied to both simulations and experiments. Due to the sparsity of PA images, segmentation focuses Hybrid-BCNN on minimizing the loss function in regions with PA signals for better predictions. The results show that accurate PA segmentations and images are obtained, and error predictions are highly statistically correlated to actual errors. To leverage error predictions, confidence processing created PA images above a specific confidence level.

Sequential Two-Mode Fusion Underwater Single-Photon Lidar Imaging Algorithm

Aiming at the demand for long-range and high-resolution imaging detection of small targets such as submerged submarine markers in shallow coastal waters, research on single-photon lidar imaging technology is carried out. This paper reports the sequential two-mode fusion imaging algorithm, which has a strong information extraction capability and can reconstruct scene target depth and reflection intensity images from complex signal photon counts. The algorithm consists of four steps: data preprocessing, extremely large group value estimation, noise sieving, and total variation smoothing constraints to image the target with high quality. Simulation and test results show that the imaging performance and imaging characteristics of the method are better than the current high-performance first-photon group imaging algorithm, indicating that the method has a great advantage in sparse photon counting imaging, and the method proposed in this paper constructs a clear depth and reflectance intensity image of the target scene, even in the 50,828 Lux ambient strong light and strong interference, the 0.1 Lux low-light environment, or the underwater high-attenuation environment.