Image Gradient Research Articles

Deep learning informed diffusion equation model for image denoising

AbstractImage denoising is one of the fundamental problems in image processing. Convolutional neural network (CNN) based denoising approaches have achieved better performance than traditional methods, such as STROLLR and BM3D. However, CNNs can easily bring unexplainable artifacts to denoised images. In this article, a Deep Learning‐Informed Diffusion Equation (DLI‐DE) framework utilizing the image prior or the image gradient prior for image denoising is proposed. The image priors and gradient priors are learned from CNN models and used as coefficients in diffusion equations. The solution of DLI‐DE is infinitely smooth from the uniqueness of existence theorem, which guarantees that the denoised image is free of artifacts. Good properties of DLI‐DE also ensure high‐quality of denoising. The experimental analysis confirms that the denoising performance of DLI‐DE is comparable to that of contemporary CNN‐based denoising methods such as TNRD and DnCNN, while effectively preventing artifacts.

Enhancing LSPIV accuracy in low-speed flows and heterogeneous seeding conditions using image gradient

Flow measurement in rivers and channels is crucial for water resource management and infrastructure planning, especially under the context of climate change. However, traditional methods like mechanical current meters and hydroacoustic instruments face limitations in terms of cost, intrusiveness, and accessibility. In recent years, image-based velocimetry techniques have emerged as promising alternatives due to their non-contact nature and cost-effectiveness. Nevertheless, persistent challenges remain, particularly concerning the uniform distribution of surface tracers necessary for precise measurements. These challenges are particularly pronounced in cases involving artificial seeding, where ensuring uniform distribution poses a significant obstacle. To address this issue, this study presents a novel methodology for filtering Large Scale Particle Image Velocimetry (LSPIV) data based on indicators of pixel intensity gradients. The methodology was evaluated across various field measurements under low flow conditions, encompassing a wide range of seeding characteristics. The evaluations demonstrated improvements in mean surface velocity profile estimation, showing reductions of up to 70 % in normalized root mean square error compared to not using filters. Additionally, the results were compared with filters typically employed by experienced LSPIV users, such as background subtraction and cross-correlation coefficient thresholds, showing improvements with the proposed filter. Implementation of the proposed strategy reduces the subjectivity in LSPIV implementation, particularly for users with limited knowledge of the technique, but also require minimal post-processing efforts. The methodology is anticipated to be integrated into existing software tools, thereby enhancing the accessibility of LSPIV for individuals with limited expertise in image velocimetry. Overall, this methodology facilitates cost-effective expansion of hydrological information availability, particularly in resource-constrained regions.

Approximate Observation Weighted ℓ2/3 SAR Imaging under Compressed Sensing.

Compressed Sensing SAR Imaging is based on an accurate observation matrix. As the observed scene enlarges, the resource consumption of the method increases exponentially. In this paper, we propose a weighted ℓ2/3-norm regularization SAR imaging method based on approximate observation. Initially, to address the issues brought by the precise observation model, we employ an approximate observation operator based on the Chirp Scaling Algorithm as a substitute. Existing approximate observation models typically utilize ℓq(q = 1, 1/2)-norm regularization for sparse constraints in imaging. However, these models are not sufficiently effective in terms of sparsity and imaging detail. Finally, to overcome the aforementioned issues, we apply ℓ2/3 regularization, which aligns with the natural image gradient distribution, and further constrain it using a weighted matrix. This method enhances the sparsity of the algorithm and balances the detail insufficiency caused by the penalty term. Experimental results demonstrate the excellent performance of the proposed method.

Investigating the Influence of Wavelength-Specific Textured Backgrounds in Background Oriented Schlieren (BOS) Imaging

This study investigates the influence of wavelength-specific textured backgrounds on the effectiveness of Background-Oriented Schlieren (BOS) imaging, focusing on wavelengths from 400 nm to 670 nm at intervals of 30 nm intervals and multiple captured recordings for each background wavelength interval. By analyzing the signal-to-noise ratio (SNR) computationally, and the image gradient magnitude, we aimed to determine the optimal wavelengths for capturing turbulence and determine the effectiveness of colored backgrounds in natural external environments for schlieren. The SNR, calculating the ratio of mean signal intensity to noise standard deviation, revealed the highest value at 550 nm (SNR = 22.8), indicating maximized clarity. Similarly, image gradient magnitude, computed using the Sobel operator to assess spatial intensity changes, peaked at 550 nm (G=52.3), confirming effective turbulence visualization. Our findings align with the Bayer color filter trend, suggesting that the green spectrum is particularly advantageous for BOS imaging. Deviations at 490 nm and 580 nm, characterized by lower SNR and gradient magnitude, could be attributed to atmospheric scattering, refractive index overlap, or slight digital video capture differences., highlighting environmental factors that can influence imaging performance and value variation. These insights emphasize the importance of wavelength selection and background design in real-world BOS applications, suggesting that while 550 nm provides optimal results, further refinement may enhance the effectiveness of other wavelengths.

Efficient participating media rendering with differentiable regularization

Highly scattering media, such as milk, skin, and clouds, are common in the real world. Rendering participating media is challenging, especially for high-order scattering dominant media, because the light may undergo a large number of scattering events before leaving the surface. Monte Carlo-based methods typically require a long time to produce noise-free results. Based on the observation that low-albedo media contain less noise than high-albedo media, we propose reducing the variance of the rendered results using differentiable regularization. We first render an image with low-albedo participating media together with the gradient with respect to the albedo, and then predict the final rendered image with a low-albedo image and gradient image via a novel prediction function. To achieve high quality, we also consider the gradients of neighboring frames to provide a noise-free gradient image. Ultimately, our method can produce results with much less overall error than equal-time path tracing methods.

Experimental evaluation of green nanofluids in heat exchanger made oF PDMS

Conventional methods for synthesizing metallic nanoparticles face challenges such as instability and environmental concerns. Therefore, new, simpler, and more eco-friendly methods are being explored. In this context, the study reports a green synthesis process to produce magnetic iron oxide nanoparticles using an aqueous extract of the alga Chlorella vulgaris. This process leverages natural resources to create a sustainable nanofluid known as green nanofluid. To evaluate the characteristics of this nanofluid, experimental measurements of wettability, viscosity, thermal conductivity, and qualitative stability analysis were conducted. An experimental setup consisting of a heat exchanger made of polydimethylsiloxane (PDMS) was used to assess the thermal performance and the results were compared to theoretical equations and numerical simulation. Additionally, thermographic imaging of temperature gradients as the fluids passed over the heated surface of the serpentine channel were made. The main findings confirmed that the nanofluid was more stable than that obtained by traditional methods and had a more uniform temperature distribution over the heat exchanger. The higher concentration exhibited superior thermal performance compared to DI-Water. Moreover, the green nanofluid was used at a weight concentration of 0.1 wt%, provided thermal performance results of nearly 4.5% superior to those estimated by the numerical model and 6.4% higher than those experimentally obtained with the base fluid, respectively. Finally, the results obtained for the nanofluid also showed an average increase of around 5% in the viscosity of the base fluid, with a more significant sedimentation at a concentration of 0.1 wt%.

Batik Pattern Classification Using Machine Learning Approaches

Batik is one of Malaysia traditional textile art form that is well known. By using Artificial Neural Network (ANN), k-Nearest Neighbors (k-NN) and Decision Tree methods, this study aims to classify Kelantan batik designs according to flora, fauna and geometry motifs. 133 images of the three categories were collected from social media and underwent pre-processing techniques. Image augmentation was done to enhance the diversity and quality of available training data for machine learning models. Digital transformation on the images based on colour features was developed to classify the three types of batik motifs. Image embedding was employed which returned a vector representation of each image in a data table in Orange software. The data divided into training and testing dataset, with a ratio of 8:2. The performance of each machine learning techniques were compared. The findings showed that ANN produced an excellent performance as indicated by classification accuracy (CA) of 87.9% for original images and 82.2% using Luminance Gradient image transformation technique. ANN also returns the highest AUC score indicating it is the best in distinguishing the images motif. Results from confusion matrix showed that ANN have the least misclassification for batik classification. Based on the result, it signifies that ANN performs the best classification among the three approaches.

Bilateral fusion low‐light image enhancement with implicit information constraints

AbstractResearch on low‐light image enhancement focuses on improving image quality in dim conditions. Recently, deep learning has driven significant advancements, with many studies using neural networks to enhance low‐light images. However, most focus on complex network designs to increase nonlinearity, often neglecting the implicit information from local image transformations. This paper introduces an improved U‐net‐based method for low‐light enhancement, retaining the original encoding network and adding branch links in the decoding network. The method uses attention feature fusion to handle image noise and gradients separately, adjusting brightness through a gradient‐adaptive transform. This approach optimizes performance using loss functions like peak signal‐to‐noise ratio and colour consistency. Unlike previous methods, the approach emphasizes extracting implicit information from image gradients, achieving enhancement that aligns with the original brightness distribution. The result is enhanced images with high detail similarity to the original, achieved through end‐to‐end inference in experiments.

A Novel Fractional-Order Non-Convex TVα,p Model in Image Deblurring

In this paper, we propose a non-convex model with fractional-order applied to image deblurring problems. In the new model, fractional-order gradients have been introduced to preserve detailed features, and a source term with a blurry kernel is used for deblurring. This aspect of the model ensures that it can handle various blurring scenarios. Additionally, we devise an algorithm that maintains the non-expansiveness of the support set for image gradients, serving as a critical component in our approach to address image deblurring issues. After approximate linearization, the algorithm can be easily implemented. Some standard image processing techniques similar to fast Fourier transform can be utilized. Global convergence has likewise been confirmed and established. Moreover, we have also demonstrated that the proposed deblurring algorithm exhibits edge preservation properties. Compared with several existing classic models, the proposed method maintains a good balance between detail preservation, edge preservation, and deblurring. In addition, compared with several classic methods, the proposed method improved PSNR and SSIM by 0.9733 and 0.0111, respectively.

Multiobjective optimization guided by image quality index for limited-angle CT image reconstruction.

Due to the incomplete projection data collected by limited-angle computed tomography (CT), severe artifacts are present in the reconstructed image. Classical regularization methods such as total variation (TV) minimization, ℓ0 minimization, are unable to suppress artifacts at the edges perfectly. Most existing regularization methods are single-objective optimization approaches, stemming from scalarization methods for multiobjective optimization problems (MOP). To further suppress the artifacts and effectively preserve the edge structures of the reconstructed image. This study presents a multiobjective optimization model incorporates both data fidelity term and ℓ0-norm of the image gradient as objective functions. It employs an iterative approach different from traditional scalarization methods, using the maximization of structural similarity (SSIM) values to guide optimization rather than minimizing the objective function.The iterative method involves two steps, firstly, simultaneous algebraic reconstruction technique (SART) optimizes the data fidelity term using SSIM and the Simulated Annealing (SA) algorithm for guidance. The degradation solution is accepted in the form of probability, and guided image filtering (GIF) is introduced to further preserve the image edge when the degradation solution is rejected. Secondly, the result from the first step is integrated into the second objective function as a constraint, we use ℓ0 minimization to optimize ℓ0-norm of the image gradient, and the SSIM, SA algorithm and GIF are introduced to guide optimization process by improving SSIM value like the first step. With visual inspection, the peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and SSIM values indicate that our approach outperforms other traditional methods. The experiments demonstrate the effectiveness of our method and its superiority over other classical methods in artifact suppression and edge detail restoration.

Evaluation of cavitation phenomena in three-way globe valve through computational analysis and visualization test

A three-way valve has a multi-port structure with three openings, which allows control of the fluid direction. However, owing to the complicated trim shape of the internal flow, an irregular fluid flow occurs, which hinders precise fluid flow control. In severe cases, cavitation induces mechanical damage owing to abrupt changes in the fluid direction. In this study conducted a computational fluid dynamics (CFD) analysis was performed to estimate the localized cavitation around the bottom plug of the three-way valve. To quantify localized cavitation, the percentage of cavitation (POC) was derived using the vapor volume fraction (VVF). The POC, defined by the cavitation occurrence zone with VVF > 0.5 divided by the volume of the cavitation danger zone, was 34.90%. Cavitation at this POC level could cause mechanical damage; therefore, a size optimization was performed. The lengths of the optimized waist and tail regions of the bottom plug were obtained wherein the POC level decreased by 19.06%. In addition, experiments were conducted using a flow visualization test setup. The experimental results were quantified into the POC employing the image gradients method, and the results were in good agreement with the CFD analysis.

Label-free 3D molecular imaging of living tissues using Raman spectral projection tomography

The ability to image tissues in three dimensions (3D) with label-free molecular contrast at the mesoscale would be a valuable capability in biology and biomedicine. Here, we introduce Raman spectral projection tomography (RSPT) for volumetric molecular imaging with optical sub-millimeter spatial resolution. We have developed a RSPT imaging instrument capable of providing 3D molecular contrast in transparent and semi-transparent samples. We also created a computational pipeline for multivariate reconstruction to extract label-free spatial molecular information from Raman projection data. Using these tools, we demonstrate imaging and visualization of phantoms of various complex shapes with label-free molecular contrast. Finally, we apply RSPT as a tool for imaging of molecular gradients and extracellular matrix heterogeneities in fixed and living tissue-engineered constructs and explanted native cartilage tissues. We show that there exists a favorable balance wherein employing Raman spectroscopy, with its advantages in live cell imaging and label-free molecular contrast, outweighs the reduction in imaging resolution and blurring caused by diffuse photon propagation. Thus, RSPT imaging opens new possibilities for label-free molecular monitoring of tissues.

GAN-HA: A generative adversarial network with a novel heterogeneous dual-discriminator network and a new attention-based fusion strategy for infrared and visible image fusion

Infrared and visible image fusion (IVIF) aims to preserve thermal radiation information from infrared images while integrating texture details from visible images. Thermal radiation information is mainly expressed through image intensities, while texture details are typically expressed through image gradients. However, existing dual-discriminator generative adversarial networks (GANs) often rely on two structurally identical discriminators for learning, which do not fully account for the distinct learning needs of infrared and visible image information. To this end, this paper proposes a novel GAN with a heterogeneous dual-discriminator network and an attention-based fusion strategy (GAN-HA). Specifically, recognizing the intrinsic differences between infrared and visible images, we propose, for the first time, a novel heterogeneous dual-discriminator network to simultaneously capture thermal radiation information and texture details. The two discriminators in this network are structurally different, including a salient discriminator for infrared images and a detailed discriminator for visible images. They are able to learn rich image intensity information and image gradient information, respectively. In addition, a new attention-based fusion strategy is designed in the generator to appropriately emphasize the learned information from different source images, thereby improving the information representation ability of the fusion result. In this way, the fused images generated by GAN-HA can more effectively maintain both the salience of thermal targets and the sharpness of textures. Extensive experiments on various public datasets demonstrate the superiority of GAN-HA over other state-of-the-art (SOTA) algorithms while showcasing its higher potential for practical applications.

RETNet: Resolution enhancement Transformer network for magnetic particle imaging based on X-space

Magnetic Particle Imaging (MPI) can visualize the concentration distribution of superparamagnetic iron-oxide nanoparticles (SPIONs) in tissues with the advantages of high sensitivity and high temporal resolution. However, the low spatial resolution of MPI limits its application. Increasing the gradient strength of the selection field can improve the resolution of MPI, but also increase power consumption and noise. A feasible and cost-effective method to address this limitation is to reconstruct high gradient (HG) image from low gradient (LG) image using algorithms. Deep learning has been a powerful tool for improving the resolution of medical imaging techniques. In this study, we propose a Resolution Enhancement Transformer Network (RETNet) for reconstructing HG image with high-resolution from LG image with low-resolution as input, avoiding high power consumption and high noise in the system with HG field. RETNet leverages a shallow feature extractor to capture shallow features, a cross-scale-Transformer (CST) to focus on textural features, a residual-swin-Transformer (RST) to focus on structural features, and an image reconstruction module to aggregate these three types of features and reconstruct the HG image. Textural and structural features extracted can ensure the integrity of the details and the realization of high definition in the reconstructed image. Ablation experiments demonstrate the significant contribution of these two modules to reconstruct the HG image. Comparative experiments, including experiments at noise-free and multiple noise levels, confirm the high robustness of RETNet. Simulation, phantom, and in vivo experiments consistently demonstrate that RETNet outperforms competing methods and effectively improves the resolution of MPI.

Hyperspectral image restoration using noise gradient and dual priors under mixed noise conditions

AbstractImages obtained from hyperspectral sensors provide information about the target area that extends beyond the visible portions of the electromagnetic spectrum. However, due to sensor limitations and imperfections during the image acquisition and transmission phases, noise is introduced into the acquired image, which can have a negative impact on downstream analyses such as classification, target tracking, and spectral unmixing. Noise in hyperspectral images (HSI) is modelled as a combination from several sources, including Gaussian/impulse noise, stripes, and deadlines. An HSI restoration method for such a mixed noise model is proposed. First, a joint optimisation framework is proposed for recovering hyperspectral data corrupted by mixed Gaussian‐impulse noise by estimating both the clean data as well as the sparse/impulse noise levels. Second, a hyper‐Laplacian prior is used along both the spatial and spectral dimensions to express sparsity in clean image gradients. Third, to model the sparse nature of impulse noise, an ℓ1 − norm over the impulse noise gradient is used. Because the proposed methodology employs two distinct priors, the authors refer to it as the hyperspectral dual prior (HySpDualP) denoiser. To the best of authors' knowledge, this joint optimisation framework is the first attempt in this direction. To handle the non‐smooth and non‐convex nature of the general ℓp − norm‐based regularisation term, a generalised shrinkage/thresholding (GST) solver is employed. Finally, an efficient split‐Bregman approach is used to solve the resulting optimisation problem. Experimental results on synthetic data and real HSI datacube obtained from hyperspectral sensors demonstrate that the authors’ proposed model outperforms state‐of‐the‐art methods, both visually and in terms of various image quality assessment metrics.

Towards strain gauge 2.0: Substituting the electric resistance routinely deposited on polyimide film by the optimal pattern for full‐field strain measurement

AbstractThe checkerboard constitutes the best pattern for full‐field strain measurement because it maximizes image gradient. In the experimental mechanics community, employing this pattern is currently strongly limited because depositing it on the surface of specimens raises practical difficulties. A recent study shows, however, that it is technically possible by using a laser engraver. The present paper aims to push this solution forward by printing a checkerboard pattern on a thin polymeric film and then gluing the resulting laser‐engraved film on the specimen surface. The underlying idea is to separate the manufacturing process of this optical strain gauge on the one hand and its use on the other hand to help spread this strain measuring tool in the experimental mechanics community. The polymeric film employed here is the same as that used in the manufacturing process of classic electrical gauges, so one can rely on the know‐how of classic strain gauge bonding to glue this optical strain gauge on the specimen surface. The main difference between the proposed tool and classic electrical gauges is that the strain field beneath the polymeric support is measured instead of localized strain values. The paper is a proof of concept for this strain field measuring tool. The manufacturing and bonding processes are described in the paper. The localized spectrum analysis, a spectral technique developed for processing images of periodic patterns, is used to retrieve the strain fields from checkerboard images. Through two complementary examples, we show the ability of this new type of strain gauge to detect and quantify local details in the strain field beneath. A simplified 1D model is also proposed to assess the minimum width of the strain peak that can reliably be measured with this technique.

Dual-Vector Aeromagnetic Survey-Based Gradient Imaging and Detection of Target Magnetic Anomaly

Dual-Vector Aeromagnetic Survey-Based Gradient Imaging and Detection of Target Magnetic Anomaly

Impact of cerebral microbleeds on bleeding and outcome after stroke thrombolysis

BackgroundCerebral microbleeds may be responsible for bleeding and poor functional outcome following thrombolysis of acute ischemic stroke. We tried to assess the association between cerebral microbleeds, hemorrhagic complication and functional outcome following intravenous thrombolysis in Egyptian acute ischemic stroke patients. We evaluated 66 acute ischemic stroke patients treated with intravenous thrombolysis for cerebral microbleeds using T2* weighted Magnetic Resonance Imaging Gradient echo. Distribution, number, and predictors of microbleeds were assessed. The effect of microbleeds presence and burden on development of hemorrhage after thrombolysis and 90 days functional outcome was evaluated.ResultsOut of 66 stroke patients treated with intravenous thrombolysis, 33 patients had microbleeds. Multivariate analysis shows that hypertension, diabetes mellitus, atrial fibrillation, smoking and leukoaraiosis were independently associated with microbleeds. Post-thrombolysis symptomatic intracerebral hemorrhage occurred in 12/66 (18.1%). Multivariate analysis shows that high burden microbleeds (≥ 10), leukoaraiosis, stroke severity, delayed thrombolysis were independently associated with intracerebral hemorrhage. Post-thrombolysis hemorrhage was statistically higher in microbleeds group (51.5%) than non-microbleeds group (9.1%) (p < 0.001). Parenchymal hemorrhage represents (58.8%) of hemorrhagic cases in microbleeds group in comparison to (33.3%) of non-microbleeds group (p = 0.62). Parenchymal hemorrhage represents (50%) of hemorrhagic cases with microbleeds < 10, while it represents (100%) of hemorrhagic cases with microbleeds ≥ 10. Favorable modified Rankin Scale (0–2) was more prevalent in non-microbleeds group (72.7%) than microbleeds group (45.5%) at 90 days (p = 0.024). Favorable outcome at discharge and at 90 days was statistically more prevalent in patients with microbleeds < 10 (p = 0.004).ConclusionHigh burden cerebral microbleeds should be considered a risk for parenchymal hemorrhage following intravenous thrombolysis. The presence and burden of microbleeds may affect prognosis 90 days after thrombolytic therapy.

Primal-dual hybrid gradient image denoising algorithm based on overlapping group sparsity and fractional-order total variation

This study introduces a non-convex fractional-order hyper-Laplacian variational model for Gaussian noise removal. It employs first the primal-dual hybrid gradient algorithm to solve problems involving overlapping group sparse structures. Additionally, this paper designs a new algorithm leveraging the framework of the Chambolle-Pock algorithm with convergence and aims to recover high-quality images. The model, integrating the overlapping group sparse structure of the hyper-Laplacian prior with the non-convex fractional-order total variation, exhibits superior performance in reducing the staircase effect and maintaining sharp edge contours. To further improve the performance of the algorithm, a semi-adaptive p(x) non-convex penalty weight assignment mechanism is designed by introducing the structure tensor, which according to the characteristics of each region of the image and the noise level. The effectiveness and superiority of the proposed algorithm in image denoising with simulation experiments and comparative analyses are fully verified.

Hybrid similarity measure-based image indexing and Gradient Ladybug Beetle optimization for retrieval of brain tumor using MRI

Hybrid similarity measure-based image indexing and Gradient Ladybug Beetle optimization for retrieval of brain tumor using MRI