Search Results (370)

Degraded tax forms and other legal–administrative documents require restoration methods that impose strict constraints on content fidelity. This paper presents a structure-aware restoration framework for degraded tax documents that combines geometric normalization, canonical template guidance, and supervised image restoration within a common alignment space. Documents are first mapped to a canonical layout through homography estimation based on Scale-Invariant Feature Transform (SIFT) and Random Sample Consensus (RANSAC), using the canonical visual template as the reference. Restoration is then performed using template priors and masked constraints designed to preserve the fixed document structure while recovering variable content. Under a fixed-budget comparative protocol, U-Net with template priors achieved the highest visual and structural quality, whereas the proposed hybrid model obtained the best functional OCR performance on synthetic data, reaching a Character Error Rate (CER) of 0.1091 and a Word Error Rate (WER) of 0.3495. As a complementary evaluation on 37 real-world documents with human-generated textual ground truth, restoration increased full-page word coverage across all three OCR engines evaluated, yielding absolute improvements ranging from 4.15 to 18.05 percentage points. Full article

Although research on lightweight monocular depth estimation models has been actively conducted, achieving real-time deployment on edge devices remains challenging due to limited computational resources and memory capacity. To address these limitations, we propose a lightweight model for self-supervised monocular depth estimation. We cut the iterations of each feature-extracting block nearly in half, while our proposed Asymmetric Dilated Convolution module and a StarNext module compensate for the reduced model capacity. Specifically, the Asymmetric Dilated Convolution module captures horizontal and vertical structural features through asymmetric kernels, and the StarNext module fuses multi-scale features via element-wise multiplication. In model training, random cropping and scaling are applied for inducing the model to focus on localized object features. Additionally, we introduce a Disparity-guided Cutout technique based on the pre-inferred disparity map to randomly mask adjacent pixels. Simulation results on the KITTI dataset demonstrate that the proposed model reduces the number of parameters and GFLOPs by approximately 50% and 58%, respectively, without significant degradation in depth estimation accuracy compared to the baseline Lite-Mono. Furthermore, inference benchmarks on the Jetson Orin Nano platform demonstrate speedups of approximately 46.0%, 46.1%, 46.3%, and 52.0% across the MaxN, 25 W, 15 W, and 7 W power modes, respectively. Full article

Graph neural networks remain challenging to apply to traffic forecasting, often failing to consistently outperform simple baselines. We observe that the strongest baseline is regime-dependent: last-value persistence dominates at short horizons on smooth freeway data, while time-of-day climatology prevails at longer horizons and on bursty arterial networks. Rather than treating this as a limitation, we propose a learnable approach that automatically selects the optimal baseline. Our method anchors predictions to a learned, per-horizon convex blend of persistence and climatology, introducing only twelve scalar parameters. This learned anchor recovers whichever baseline is locally most effective, allowing the model to focus on capturing residual variations that neither baseline captures. We evaluate on six public benchmarks (METR-LA, PEMS-BAY, PEMS03/04/07/08) spanning traffic speed and flow data under standard 70/10/20 chronological splits with masked evaluation metrics and holiday-aware climatology. Our anchored temporal models consistently beat both baseline methods on the 12-step average across all datasets, and outperform at every horizon on five of the six benchmarks. When integrated into two strong architectures (STID and Graph WaveNet), the anchor yields substantial gains at long horizons where climatology is most informative. Notably, within our lightweight framework, learned spatial graph components do not improve accuracy and can slightly degrade performance, a finding we analyze and discuss. Full article

(1) Background: Whether spatial predictive patterns in non-communicable disease mortality persist after accounting for socio-demographic development and biomarkers remains understudied in East Africa. (2) Methods: This study used heterogeneous graph transformer (HGT) models and other techniques to model spatial patterns in cause- and sex/age-specific mortality (hypertensive heart disease [HHD], ischaemic heart disease [IHD], stroke, and diabetes), incorporating risk factors and socio-demographic development (SDI), using data from the Global Burden of Disease (GBD) study, 1990–2023, across Burundi, Kenya, Rwanda, Tanzania, and Uganda. (3) Results: HGT achieved higher performance than OLS spatial lag benchmarks (R² 0.948–0.970 vs. 0.194–0.376). Spatial predictive patterns were disease-specific. Stroke was the only disease with consistent positive spatial structure (SDI-only: 0.645%, 95% CI [0.380, 0.907]), with spatial structure strengthening after 2015. HHD exhibited severe and stable degradation (Risk-only: −137.892%, 95% CI [−181.908, −96.380]), driven by the interaction between metabolic risk covariates and geographic adjacency. Diabetes showed consistently severe degradation (SDI + Risk: −201.941%, 95% CI [−257.349, −150.082]). IHD patterns were weak and unstable. Sex disaggregation revealed stronger stroke spatial signals, indicating latent sex-specific patterns masked by aggregation. GBD measurement uncertainty contributed less than 0.025% of result variance, with model randomness dominating. (4) Conclusions: Spatial predictive patterns in NCD mortality in East Africa are disease-specific. Stroke shows emerging cross-border spatial structure after 2015, while HHD and diabetes reflect country-specific determinants. Sex-disaggregated graph construction reveals latent spatial heterogeneity invisible to aggregate models, supporting disease-specific, sex-stratified regional health strategies. Full article

Screen content images (SCIs) exhibit complex structural heterogeneity, rendering traditional statistics-based natural scene image quality assessment (NR-IQA) metrics ineffective. Although deep learning models achieve high prediction accuracy, their prohibitive computational demands preclude deployment in latency-sensitive industrial scenarios. While existing handcrafted lightweight SCI-IQA metrics reduce computational overhead, most rely on unsegmented global feature pooling or holistic edge statistics (e.g., edge histograms or Fisher vector coding), thereby diluting locally critical text-edge distortions in vast homogeneous backgrounds. To address this limitation, we propose an ultra-lightweight, deep-learning-free NR-IQA framework centered on human visual masking. Unlike existing lightweight methods, our approach explicitly employs dual-scale Canny edge operators to partition SCIs into edge-sensitive and flat background regions. Guided by this visual prior, structural degradations and micro-compression textures are extracted region-wise using Sobel gradients and uniform local binary patterns (LBPs) and aggregated with global Commission Internationale de I’Eclairage L*a*b*(CIELAB) color statistics into a compact 60-dimensional descriptor. A grid-search-optimized Support Vector Regression (SVR) maps these features to subjective quality scores. Extensive cross-validation on the SIQAD and SCID datasets demonstrates that our metric outperforms existing handcrafted lightweight SCI metrics and traditional NSS models, while achieving accuracy competitive with representative full-reference metrics. Consuming only 79.3 ms per image on a standard CPU, it offers a practical accuracy–efficiency trade-off for resource-constrained periodic quality monitoring. Full article

Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance and safe aero-engine operation. To address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies, this study proposes a degradation-aware dynamic masking augmentation method combined with a multiscale CNN–Transformer network. The 21 sensor variables in the NASA C-MAPSS dataset are first grouped by physical meaning and reconstructed into four-dimensional state features. A degradation-state score integrating local variance and trend slope is then used to adapt temporal masking probabilities across degradation stages, while feature masking probabilities are assigned according to feature importance. Masked positions are filled with adjacent unmasked observations, and invalid augmented samples are removed through trend consistency verification. A multiscale CNN with channel attention extracts local degradation features, and a Transformer encoder captures temporal dependencies. Bayesian optimization is used to determine key hyperparameters. On FD001, the proposed method achieves an MSE of 348.3970, an MAE of 8.3908, and an R² of 0.9227, reducing MSE and MAE by 4.27% and 28.42%, respectively, compared with ML-RFR. It also achieves the highest R² of 0.9369 on FD003. Cross-dataset and multi-seed experiments further confirm its applicability and stability. Full article

In high-resolution wide-swath (HRWS) spaceborne synthetic aperture radar (SAR) systems, clustered phased array (CPA) architectures alleviate hardware costs but face critical subarray synthesis challenges: manually prescribed pattern masks, redundant equality matching, and unrealizable crossover topologies. This paper proposes a mask- and contiguity-constrained power pattern matching method (MC-PMM) to address these limitations. First, a semidefinite programming (SDP) procedure constructs an SAR-metric-aware SDP-relaxed reference mask for the noise equivalent sigma zero (NESZ) and range ambiguity-to-signal ratio (RASR) requirements within the relaxed covariance space. Second, a dynamic programming (DP) strategy is integrated with a novel mask-constrained iterative projection method (Mask-IPM) to optimize physically contiguous partitions and weights. By transforming equality waveform fitting into mask-violation-based inequality matching, MC-PMM focuses restricted spatial degrees of freedom onto critical performance boundaries. Simulations on a 64-element array demonstrate that, at a subarray ratio of $3/4$, MC-PMM achieves a 100% crossover-free topology. Furthermore, relative to the conventional equality matching framework, it lowers the mean RASR by $24.50$ dB, with a negligible worst-case NESZ degradation of under $0.4$ dB. Full article

Traditional Digital Twins (DTs) in energy sectors lack cyber-threat awareness, while cybersecurity DTs overlook downstream physical impacts. Loosely coupled co-simulations attempt to bridge this gap but introduce computational lags that mask critical cross-domain vulnerabilities. To address these limitations, this paper proposes a unified, tightly coupled Virtual Digital Twin (VDT) framework that integrates energy systems and cybersecurity domains into a single environment. The methodology models the precise mathematical, thermal, and electrical constraints of key assets to capture cross-domain feedback loops. Specifically, a power transformer and a microgrid-connected inverter serve as case studies to map cyberattack vectors directly onto physical definitions. Numerical simulation evaluates multiple threat scenarios, including supervisory, measurement, and physical-level (harmonic) attacks on the transformer, alongside short-circuit and hybrid phase-harmonic attacks on the inverter. Results show how subtle digital disruptions propagate past communication layers to induce physical degradation and operational stress. By explicitly detailing the governing equations and providing sensitivity analyses, this work delivers a transparent, high-fidelity methodology for protecting critical cyber–physical infrastructures from asset-destructive manipulations. Full article

Geometric misalignment degrades industrial cone-beam computed tomography (CBCT), particularly when a dedicated calibration phantom cannot be deployed during object acquisition. This study presents a three-stage, scan-specific geometric refinement framework that searches a bounded five-coordinate correction space around a nominal geometry. Coarse candidates are screened using the normalized residual between a geometry-corrected center-of-mass trajectory and its best-fitting low-order periodic model. Translation- and rotation-dominant coordinates are then refined within system-specific physical bounds, and an energy-normalized nuclear-norm score of corrected row-wise sinograms is used for local correlation refinement. The periodic and low-rank terms are treated as object-dependent surrogate objectives rather than as standalone guarantees of physical parameter identifiability. An exact-ASTRA implementation check using a Shepp–Logan volume verified the detector-plane reindexing convention: applying the injected correction reduced valid-mask projection discrepancy to 35.2%, 13.7%, and 8.66% of the uncorrected values for small, medium, and large perturbations, respectively, with round-trip resampling NRMSE of 0.022–0.023 and a mean valid fraction of 98.4%. Three industrial datasets acquired with horizontal gantry CT, temperature-stage in situ CT, and vertical micro-CT provided comparative reconstruction evidence. In addition, a controlled reduced-resolution industrial object reprojection benchmark was used for direct comparison with MI-PSO, PR, and a stability-regularized implementation of the public epipolar-consistency formulation (Open-ECC-R). Over 20 fixed-ROI axial slices, Open-ECC-R increased the mean SSIM from 0.6852 ± 0.0454 for the uncalibrated reconstruction to 0.8450 ± 0.0155 and reduced the NRMSE from 0.5180 ± 0.0526 to 0.1671 ± 0.0125. The proposed method achieved the highest mean SSIM of 0.9933 ± 0.0002 and the lowest NRMSE of 0.0321 ± 0.0009. For the Bluetooth earphone dataset, local sagittal and axial MTF₅₀ estimates increased from 0.84 to 0.94 lp/mm and from 0.45 to 1.05 lp/mm, respectively. These results support scan-specific image-quality refinement around a nominal geometry while avoiding unsupported claims of absolute parameter recovery. Full article

In response to degraded parking slot markings caused by wear and tear, water accumulation, or occlusion, which significantly impair the perception accuracy and localization robustness of automated parking systems, this paper proposes SlotNet, a lightweight enhancement network. The proposed method incorporates a skeleton-driven adaptive width completion algorithm to mitigate segmentation errors and restore the topological continuity of fractured parking slot lines. The network integrates three lightweight modules: Lightweight Reparameterized VGG (LightRepVGG) for enhancing the extraction of fine-grained structural features via structural reparameterization, Parallel Perceptual Structured Attention—Light (PASA_Light) for multi-scale feature fusion, and Adaptive Decoupled Detect and Segment (AdaDecDS) for anchor-free decoupled detection and segmentation. The experimental results show that SlotNet achieves an inference speed of 65.75 Frames Per Second (FPS). The mask average precision (mask mAP@0.5) reaches 90.2% under an Intersection over Union (IoU) threshold of 0.5, enabling robust completion and accurate detection of degraded parking slot lines. Compared with existing detection, SlotNet achieves a superior balance among accuracy, robustness, and real-time performance, making it suitable for deployment on embedded in-vehicle platforms. Full article

Underwater object detection remains challenging in adverse aquatic environments, where severe image degradation caused by turbidity, light scattering, color attenuation, and low illumination substantially reduces detection reliability. Although real-world underwater datasets are essential, their limited scale and environmental diversity make it difficult to cover the wide range of degraded conditions encountered in practice. To improve detection robustness without collecting additional annotations, we propose physics-aware diffusion synthesis (PADS), a framework that uses a small set of labeled real images to synthesize diverse physically plausible degraded underwater samples. PADS couples a ControlNet-conditioned latent diffusion generator with a physics-based underwater image-formation model inspired by Jaffe–McGlamery and Akkaynak optics. Semantic masks are first employed to preserve object layout during generation. Meanwhile, water-optics parameters are incorporated through cross-attention to guide the degradation process. In addition, the physical model enforces a color and attenuation consistency loss during training and serves as an SDEdit-style latent prior during synthesis. To further improve localization under degradation, especially for small objects, we introduce a training-only scale-aware focaler–NWD (SA-FNWD) bounding-box loss, which emphasizes normalized Wasserstein distance for small boxes while retaining IoU-based regression for larger objects. Experiments on the MOUD dataset demonstrate that detectors trained with PADS-synthesized data achieve substantially stronger robustness under severe degradation. At the harshest turbidity level, PADS retains 59.3% of clean accuracy compared with 14.9% for the copy–paste-based synthesis method and 14.1% for the pix2pix-based synthesis method. SA-FNWD further improves mAP@0.5:0.95 across degradation severities. These results show that physics-grounded diffusion synthesis provides the main robustness gain, while SA-FNWD offers a complementary small-object localization improvement with no inference overhead. Full article

Visible fracture detection in underground roadways is challenging because fracture targets are often elongated, weakly contrasted, irregularly distributed, and easily confused with complex rock-wall textures. In addition, uneven illumination, dust interference, and blurred boundaries further reduce the reliability of conventional crack detection and segmentation methods. To improve fracture instance segmentation under such conditions, this study proposes YOLOv13n-seg-crack, an improved lightweight instance segmentation model based on a self-constructed YOLOv13n-seg baseline. The proposed model introduces three main improvements. First, a C2f-CA module is embedded into the backbone to enhance spatial-position perception and directional feature representation for elongated fractures. Second, a shallow high-resolution branch and auxiliary feature paths, denoted as B2 + H2 + P2, are constructed to strengthen the transmission of fine edge and texture information for small and discontinuous fracture targets. Third, an Edge-aware SIoU (EA-SIoU) loss is designed by adding edge-consistency and aspect-ratio constraints, thereby improving bounding-box localization for narrow and irregular fracture regions. Experiments were conducted on the public Crack Segmentation Dataset and an expanded self-built underground roadway dataset collected at the Woniushan Experimental Base. On the public dataset, YOLOv13n-seg-crack achieved detection Precision, Recall, mAP50, and mAP50:95 of 84.56%, 65.49%, 71.51%, and 52.72%, respectively, and mask Precision, Recall, mAP50, and mAP50:95 of 74.94%, 60.38%, 59.52%, and 21.99%, respectively. Compared with YOLOv13n-seg, the detection mAP50 and mask mAP50 increased by 1.91 and 3.19 percentage points, respectively, while the model maintained an inference speed of 168.73 FPS. Repeated-seed experiments, ablation studies, and degraded-image tests further demonstrate the stability and robustness of the proposed improvements. On the self-built underground roadway dataset containing 100 images and 118 annotated fracture instances, YOLOv13n-seg-crack improved detection mAP50 from 68.72% to 73.36% and mask mAP50 from 30.76% to 33.74%. These results indicate that the proposed method provides an effective and lightweight solution for visible fracture detection and instance segmentation in complex underground roadway scenes. Full article

Multispectral remote sensing classification benefits from the complementary information carried by visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) Sentinel-2 bands, yet most deep models process them as a single stacked tensor without explicitly preserving their inter-group relationships. We propose Relation-Consistency Group Contrastive Learning (Group-CL-RC), a robustness-oriented framework combining group-level contrastive alignment with a relation-consistency regularizer defined over a compact VIS–NIR–SWIR similarity descriptor. The method is evaluated on EuroSAT All Bands using four backbones under radiometric drift, spatial masking, K-drop band removal, and compound spectral–spatial corruption (CS2C), and externally validated on Sentinel-2-only SEN12MS under standard and seasonal-shift protocols. Group-CL-RC preserves strong clean performance and yields statistically supported robustness gains over the multispectral-only baseline, with the largest improvements under K-drop and CS2C. SEN12MS supports the transfer of these robustness trends beyond EuroSAT, while showing that gains over standard Group-CL remain perturbation-dependent. Ablation studies further indicate that relation consistency is an effective robustness mechanism, particularly when spectral-group availability is degraded. Relation-deformation diagnostics show that Group-CL-RC primarily reduces decision-level sensitivity to relational distortions rather than uniformly minimizing raw deformation. Overall, inter-group relational geometry provides an interpretable and effective robustness target under controlled structured spectral and spectral–spatial degradation. Full article

Detecting naval vessels at extreme distances using infrared search and track (IRST) systems presents severe physical challenges, notably the complete loss of geometric texture and the non-linear submersion of weak target signals within high-dynamic-range sea clutter. Traditional pure data-driven convolutional neural networks (CNNs) rely heavily on visual appearances and suffer from critical feature blind spots under such extreme physical degradation. To overcome this, we propose a Physics-Aware Deep Coupling Network that shifts the detection paradigm from appearance-based feature extraction to physics-guided attribute recognition. Our method deconstructs the degraded infrared signal into three complementary physical domains: an adaptive radiation energy mapping, corresponding to the energy domain, to rescue weak targets; a bio-inspired spatial saliency filtering mechanism, corresponding to the frequency domain, to maximize the signal-to-clutter ratio; and a PSF-coherent gradient topology framework, corresponding to the gradient domain, to discriminate genuine point targets from chaotic sun glints and island edges. These processed priors, alongside the raw image, are integrated into a 4-channel tensor and fused via a Cross-Domain Attention Module, ensuring deep network coupling. To evaluate this architecture, we conduct extensive experiments on the real-world Maritime-SIRST dataset. Since the original dataset provides only pixel-level segmentation masks, we generate axis-aligned bounding-box detection labels from these masks and retrain both the proposed method and a suite of state-of-the-art YOLO detectors under a unified detection paradigm. Extensive benchmarking demonstrates that our physics-aware methodology consistently outperforms these detectors, achieving a mAP50 of 0.923 and an F1 score of 89.92%, thus providing a highly interpretable and robust solution for maritime domain awareness under extreme physical constraints. Full article

Magnesium alloys are promising candidates for biomedical implants, but their rapid corrosion limits clinical use. Simulated body fluid (SBF) is commonly used to evaluate corrosion behaviour; however, Ca-P and carbonate deposits can mask the intrinsic performance of protective coatings. Tris(hydroxymethyl)aminomethane (Tris) has been proposed as an SBF modifier, although its effect on coated magnesium remains poorly understood. While Tris modifies the buffering characteristics of the solution, it also alters the stability of Mg(OH)₂ and the precipitation equilibria of corrosion products, resulting in more aggressive corrosion conditions than standard SBF. Here, the corrosion behaviour of AZ31 alloy, a plasma electrolytic oxidation (PEO) coating, and a sol-gel sealed PEO coating was investigated in SBF with and without Tris. Electrochemical impedance spectroscopy, immersion tests, pH monitoring, and post-immersion SEM/EDS analyses were used to evaluate coating performance under physiological and aggressive conditions. The results show that AZ31 and PEO coatings exhibit higher apparent corrosion resistance in SBF without Tris due to corrosion-product stabilization and Ca-P-rich deposits that partially block electrolyte access. In contrast, SBF with Tris accelerates degradation, causing uniform corrosion of AZ31 and premature PEO failure through electrolyte penetration and coating cracking. The PEO-AR/ZTP system maintains the highest electrochemical resistance and the best protective performance in both media. Full article