Search Results (571)

In this paper, we propose a new digital filtering approach based on the FIR-Median Hybrid (FMH) structure, which incorporates an Unbiased Finite Impulse Response (UFIR) filter as its core component. The proposed filter employs spatially symmetric window configurations to reduce Gaussian noise while preserving edges in images. Although the scientific community is rapidly adopting machine-learning- and deep-learning-based filters, there are several reasons to continue developing filters based on traditional methods. For example, these methods are well understood and rely on a strong mathematical foundation. Moreover, the structure of the proposed filter is simple; thus, this type of filter may be appealing to engineers unfamiliar with the machine-learning field. The performance of the proposed filter was assessed using two datasets: the first consisted of a set of artificial binary images, and the second comprised a subset of the BOWS image dataset. We conducted three main experiments. In the first experiment, we fine-tuned the filter considering three window-shape configurations. In the second experiment, Gaussian noise was added to the images, and the proposed filter was compared against other filters using edge-preservation-oriented metrics such as the Structural Similarity Index Measure (SSIM), the Normalized Step Edge Response (NSER), and the Gradient Conduction Mean Square Error (GcMSE), among others. The third experiment evaluated the performance of the best-performing window-shape configurations. This final test was assessed quantitatively using the Friedman test to identify the best-performing structure, whereas qualitative assessment was conducted using a Mean Opinion Score (MOS) test. The results show that the proposed filter achieved improved performance according to the PSNR, SNR, RMSE, and GcMSE metrics. These findings suggest that the proposed filter can be used in practical applications such as image enhancement, computer vision, and edge-detection-based preprocessing. Full article

The increasing demand for better fruit flavor and eating quality has driven the need for rapid and non-destructive assessment of internal attributes to support fruit grading and precision supply. Visible–near-infrared hyperspectral imaging (VNIR-HSI) provides rich spectral–spatial information for evaluating sweetness in citrus fruit, but its practical use is constrained by high spectral dimensionality, redundancy, and system cost. Here, we propose a reconstruction-assisted, attention-guided band-selection framework for non-destructive prediction of soluble solids content (SSC) in Shimen honey mandarins. The framework integrates spectral–spatial attention, probability-based differentiable band selection, and full-band reconstruction into a unified end-to-end architecture, enabling compact and informative band learning. Using 952 samples, the model selected 56 informative bands from the original 176-band hyperspectral data and achieved competitive SSC prediction on the test set (RMSE = 0.63 °Brix, R² = 0.80) while maintaining high-fidelity reconstruction of the full-band hyperspectral cube from the compact input (peak signal-to-noise ratio, PSNR = 36.47 dB; structural similarity index, SSIM = 0.89). These findings support the proposed framework as a methodological proof of concept for non-destructive citrus quality evaluation, indicating that substantial spectral compression can be achieved under the current VNIR setting while largely preserving predictive performance. The selected bands may provide candidate spectral regions for future compact citrus-quality sensing systems. Full article

Multispectral satellite image segmentation constitutes a challenging optimization problem due to high dimensionality and complex inter-band correlation structures. As the number of thresholds increases, the search space grows exponentially, causing metaheuristic methods to suffer from convergence instability by getting trapped in local optima on highly multimodal landscapes. In this study, a hybrid optimization method is proposed by integrating the Marine Predators Algorithm (MPA) with the Runge–Kutta (RUN) approach. The proposed framework enhances global exploration through Cauchy-based perturbation, while improving exploitation capability via a mutation-based local refinement mechanism, and reduces spectral redundancy using Principal Component Analysis (PCA). The MPA-RUN hybrid structure, combined with a Cauchy-driven exploration strategy and an adaptive local search mechanism, significantly improves the exploration–exploitation balance in multispectral image thresholding problems. Experiments are conducted on Sentinel-2 multispectral images, and the proposed method is evaluated against conventional metaheuristic algorithms over a wide threshold range (2–26), encompassing both low- and high-dimensional configurations. At high threshold levels, the proposed method achieves Peak Signal-to-Noise Ratio (PSNR) = 23.66, Structural Similarity Index Measure (SSIM) = 0.863, and Feature Similarity Index Measure (FSIM) = 0.797, while providing approximately 35% lower computational time at moderate levels, demonstrating superior efficiency. These results demonstrate that a balanced trade-off between accuracy and computational cost is achieved. The proposed approach offers a fast and reliable solution for processing high-dimensional data by effectively balancing segmentation quality and computational complexity. Full article

Synthetic aperture radar (SAR) data from Sentinel-1 enable land cover classification independent of cloud cover and illumination; however, classification performance is affected by inherent speckle noise. This study evaluates the influence of eight speckle filtering algorithms on classification accuracy using Sentinel-1 Ground Range Detected (GRD) data across five contrasting terrain types in eastern Slovakia (mountain, forest, urban, cropland, and water). Speckle suppression was assessed using Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Structural Similarity Index (SSIM), and Equivalent Number of Looks (ENL). Classification performance was quantified using Support Vector Machine (SVM), Random Forest (RF), and Histogram-based Gradient Boosting (HistGB) under VV, VH, and dual-polarization (VV + VH) configurations with repeated balanced sampling. Classification accuracy varies across terrain types. In croplands, Lee Sigma combined with SVM in VV + VH mode achieved Overall Accuracy (OA) = 0.746 ± 0.010, whereas in mountainous areas, OA = 0.838 ± 0.005 was achieved with Intensity-Driven Adaptive Neighborhood (IDAN) filtering. Urban areas achieved OA = 0.890 ± 0.006, whereas forest classification remained limited (best OA = 0.582 ± 0.011). Water surfaces approached saturation accuracy (OA ≈ 0.9998). Dual polarization improved performance in heterogeneous environments but had a limited effect in homogeneous classes. The results show that terrain structure influences the interaction between speckle filtering and classification performance. Full article

Lunar optical and synthetic aperture radar (SAR) imagery provide complementary information for characterizing the lunar surface. However, their joint use remains challenging because of substantial cross-modality differences and severe illumination constraints, particularly in polar regions. To address this challenge, we propose LS2ODiff (Lunar SAR-to-Optical Diffusion), a diffusion-based framework designed for SAR-to-optical image translation in lunar environments. LS2ODiff uses SAR observations as conditional guidance in the diffusion process and incorporates a partial-convolution strategy into the U-Net backbone to handle irregular invalid regions. In addition, self-attention modules are incorporated into the downsampling stages of the U-Net to model long-range spatial dependencies and enhance global structural consistency in complex lunar terrain. We further construct a dedicated paired dataset of the lunar south polar region by registering Chandrayaan-II DFSAR data with Lunar Reconnaissance Orbiter (LRO) Narrow-Angle Camera (NAC) imagery. Comparative experiments against Pix2Pix, CycleGAN, SynDiff, and ConDiff demonstrate that LS2ODiff achieves better visual fidelity and quantitative performance in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), Fréchet inception distance (FID), and learned perceptual image patch similarity (LPIPS). These results demonstrate the potential of diffusion models for high-fidelity lunar image translation, offering new opportunities for polar terrain interpretation and future exploration missions. Full article

Video compression is central to large-scale video delivery, where better rate–distortion efficiency directly reduces bandwidth and storage cost. A practical way to improve efficiency is to encode a low-resolution video stream with a standard codec and restore high-resolution details with a learned super-resolution model at the decoder. However, prior SR-assisted compression methods usually update the reconstruction model at fixed temporal intervals, which can waste bitrate when those update boundaries do not match actual scene changes. In this paper, we present SASVC, a scene-adaptive super-resolution video compression framework for offline codec-augmented compression. SASVC detects scene changes using frame-wise grayscale differences, updates only compact adapter modules when a content transition is observed, and compresses the resulting model updates with chained differencing, quantization, and entropy coding. In this way, the method reduces unnecessary model-stream overhead while preserving scene-specific reconstruction fidelity. Experimental results on both long-form and short-form datasets show that SASVC consistently outperforms SRVC-style baselines and conventional codec-based alternatives under the Bjontegaard delta rate based on peak signal-to-noise ratio (BD-rate/PSNR) criterion. Complementary rate–distortion (RD) comparisons in terms of structural similarity index measure (SSIM) and Video Multi-Method Assessment Fusion (VMAF) show the same overall trend, indicating that the gain is not limited to a single distortion metric. Specifically, SASVC achieves BD-rate gains of $-41.33\%$ and $-53.49\%$ on Vimeo and Xiph, respectively, and further reaches $-51.53\%$ and $-39.83\%$ on UVG and MCL-JCV. The decoder also maintains real-time 1080p reconstruction at 125 frames per second (FPS) on an NVIDIA RTX 3080 Ti GPU, indicating that scene-aligned model updates can improve compression efficiency while keeping decoder-side deployment practical. Full article

High-resolution imagery is essential for monitoring heterogeneous grassland ecosystems, yet the performance of generative adversarial network (GAN) super-resolution under varying landscape heterogeneity and operational application scenarios remains unclear. This study presents a landscape-aware evaluation of super-resolution methods in semi-arid savanna grasslands of the Edwards Plateau (Texas, USA) using paired multispectral imagery from PlanetScope (3 m) and unmanned aerial vehicle (UAV) platforms (0.03 m). Two GAN models, SRGAN and ESRGAN, were compared with a bicubic interpolation baseline. Image tiles were systematically stratified along ecologically relevant gradients of vegetation condition (NDVI quartiles), spatial structure (woody patch-based clusters), and textural complexity (GLCM entropy quartiles). Model performance was evaluated across three operational frameworks: intra-sensor downscaling, cross-sensor downscaling, and intra-to-cross generalization. Reconstruction fidelity was quantified using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), complemented by variability analysis to assess performance stability. Landscape heterogeneity strongly influenced downscaling outcomes. SRGAN performance declined in areas with dense vegetation, aggregated woody structure, and high-entropy textures, with large variability under cross-sensor and generalization scenarios. In contrast, ESRGAN demonstrated consistently robust performance across landscape gradients, whereas bicubic interpolation performed well only under intra-sensor conditions and drastically degraded under sensor transfer. These results demonstrate that vegetation condition, structural heterogeneity, and sensor-transfer scenarios jointly constrain super-resolution performance. Rather than serving as a model comparison exercise, this study emphasizes a landscape-aware framework for understanding how ecological heterogeneity and operational domain shifts jointly shape super-resolution behavior in grassland ecosystems, providing guidance for more reliable applications of deep learning-based remote sensing methods. Full article

This paper introduces a novel inertial forward–backward–forward algorithm driven by a newly conceptualized moving point projection technique for solving monotone inclusion problems in real Hilbert spaces. By leveraging the properties of a Lipschitz continuous, monotone operator and a maximally monotone operator alongside this innovative projection strategy, we dynamically construct a sequence of nonempty, closed, and convex sets that contain the zeros of the sum of the two operators. This geometric construction ensures that the resulting sequence is well defined and guarantees its weak convergence to a solution. Furthermore, to validate the practical efficacy of the proposed theoretical framework, we evaluate our method on image restoration problems. Numerical experiments measuring the improvement in signal-to-noise ratio (ISNR) and the structural similarity index measure (SSIM) confirm that the proposed algorithm is highly efficient and significantly outperforms existing state-of-the-art methods. Full article

Reliable high-fidelity video transmission over noisy quantum channels remains challenging, especially due to temporal dependencies introduced by modern video compression standards. These codecs, such as versatile video coding (VVC), employ inter-frame prediction and group-of-pictures (GOP) structures, which are highly sensitive to channel noise and can lead to error propagation across frames. Conventional quantum encoding schemes, such as Hadamard-based superposition encoding, use fixed real-valued basis transformations that provide limited phase diversity and underutilize the multi-qubit state-space, reducing robustness under noisy quantum channels. To overcome these limitations, this study proposes a multi-qubit complex-valued orthogonal unitary superposition (COUS) encoding framework for quantum video transmission. In the proposed system, VVC-compressed video bitstreams are first protected using classical channel encoding, then segmented and mapped onto multi-qubit COUS quantum states, enabling joint amplitude and phase representation with improved resilience to quantum noise. At the receiver, transmitted quantum states undergo sequential COUS decoding, channel decoding, and VVC bitstream reconstruction to recover the original video frames. The simulation results show that COUS-based multi-qubit system outperforms the Hadamard encoding-based multi-qubit system, achieving peak signal-to-noise ratio (PSNR) up to 47.22 dB, structural similarity index measure (SSIM) up to 0.9905, and video multi-method assessment fusion (VMAF) up to 96.49. Even single-qubit COUS encoding achieves 3–4 dB channel SNR gain, while higher-qubit configurations further enhance robustness and reconstructed video quality. These results confirm that the proposed framework is scalable, noise-resilient, and provides high-fidelity quantum video transmission over noisy channels. Full article

Accurate measurement of the 2D soot spatial distribution is vital for optimizing combustion efficiency and reducing pollutant emissions. While 1D laser extinction (LE) is robust and cost-effective, it provides only line-of-sight integrated information, lacking the spatial resolution required to resolve complex soot topologies. We propose Soot-MixFormer, a hybrid deep learning model designed for the high-fidelity inversion of 2D soot distributions from 1D extinction data. The architecture integrates CNN-based local feature extraction with Transformer-based global dependency modeling. Key innovations include a dynamic decoupled generation head and a Dual-Axial Gated Refinement (DAGR) module coupled with a physical hard constraint layer to ensure mass conservation and physical consistency. Experimental results demonstrate that Soot-MixFormer significantly outperforms baseline MLP and CNN models, achieving a Structural Similarity Index (SSIM) of 0.800 and a Pearson Correlation Coefficient (PCC) of 0.915, and a highly suppressed Root Mean Square Error (RMSE) representing less than 10% relative error in high-concentration zones. Furthermore, the model exhibits exceptional robustness, maintaining a cosine similarity above 0.72 even under 10% simulated measurement noise. The model is highly efficient, with only 0.97 M parameters and a real-time inference speed of ~246 FPS. This study provides a novel, low-cost diagnostic paradigm for real-time, high-accuracy monitoring of soot fields in industrial combustion environments, effectively bridging the gap between simple 1D sensing and complex 2D spatial reconstruction. Full article

The high complexity of radiation therapy for lung cancer necessitates effective planning of advanced treatments such as Volumetric Modulated Arc Therapy (VMAT) by radiation oncologists. The current VMAT treatment planning process typically involves extensive manual interaction and a time-consuming, trial-and-error, iterative approach that requires planners’ experience. This can lead to varying levels of plan quality. To improve the quality of radiotherapy treatment plans quickly and accurately, this research presents a new architecture, Enhanced UNet3D, to generate three-dimensional (3-D) dose distributions for lung cancer patients. Enhanced UNet3D utilises a symmetric encoder–decoder architecture with residual connections and a target region-attention module to achieve high accuracy in dose shaping within the PTV. A new composite objective function, Enhanced Combined Loss (ECLoss), that includes both SharpLoss, a structure-aware DVH-guided loss, and 3D gradient regularisation, has been developed to address voxel-level class imbalance and achieve realistic spatial dose falloff. This research utilised a retrospective dataset of 170 VMAT plans to train and validate the proposed model. On the test set (n = 14), the model demonstrated exceptional overall accuracy, with a Mean Absolute Error (MAE) of 0.238 ± 0.075 Gy and a structural similarity index measure (SSIM) of 0.970 ± 0.005. Moreover, the model can perform near-real-time inference at approximately 0.5 s per patient, representing a significant reduction in computational resources compared to other architectures. Therefore, these results demonstrate that the Enhanced UNet3D model with ECLoss is a clinically feasible tool for the rapid evaluation and quality assurance of radiotherapy treatment plans and may reduce the need for manual trial-and-error in VMAT workflows. Full article

Physics-guided computational imaging typically aggregates data fidelity, geometric reconstruction, and sensor consistency into a single scalar loss. In low signal-to-noise ratio (low-SNR) non-line-of-sight imaging, this centralized approach creates asymmetric gradient conflicts where the dominant constraints suppress physically meaningful updates. We propose treating multi-constraint training as a gradient coordination problem rather than scalar balancing. Our framework coordinates heterogeneous objectives through branch-wise gradient routing: soft conflict projection (PCGrad), hard physical constraint enforcement (PhysGuard), learnable sensor calibration, and a staged training protocol that decouples representation learning from nuisance parameter estimation. On held-out test scenes, the fully staged model improved the peak signal-to-noise ratio (PSNR) from 19.09 dB to 20.49 dB and the structural similarity index (SSIM) from 0.67 to 0.71 over the baseline, with consistent gains across the 48, 28, and 25 dB SNR levels. Qualitative evaluation on seven real-world scenes indicates sharper structure recovery and fewer artifacts. In this NLOS setting, gradient-level coordination is more reliable than scalar aggregation under heterogeneous constraints. Full article

To address the challenges in intuitive feature discrimination and precise quantitative evaluation of cable defects, this paper proposes a diagnostic methodology utilizing the Symmetrized Dot Pattern (SDP) transform and reflection coefficient spectra. The Dung Beetle Optimizer (DBO) is introduced to adaptively optimize the SDP transform parameters, employing the Structural Similarity Index Measure (SSIM) as a fitness function to maximize discriminability between deterioration states. Three quantitative features, including the number of effective pixels, the degree of red–blue aliasing, and radial dispersion, are extracted to characterize the physical degradation processes of signal energy accumulation, angular evolution, and path divergence. By incorporating a self-reference calibration mechanism for structural differences, features are fused into a Comprehensive Deterioration Index (CDI). Experimental results on coaxial cables simulating shielding damage and thermal aging demonstrate that SDP images reveal continuous evolution patterns corresponding to defect severity. A regression model based on these patterns effectively characterizes deterioration trends. Compared to complex models, this study achieves intuitive fault identification and preliminary quantitative description of degradation trends through image feature fusion. Although the current sample size is limited, the results validate the feasibility of this method in evaluating cable deterioration severity, offering an efficient new data-processing perspective for cable condition monitoring. Full article

Accurate delineation of tumor margins is critical for complete resection and minimizing recurrence, yet existing imaging modalities such as MRI, CT, and fluorescence imaging suffer from limitations including high cost, limited accessibility, and intraoperative constraints. In this study, we propose a low-cost, non-invasive approach for subsurface imaging based on near-infrared (NIR) illumination combined with deep learning. A controlled experimental setup was developed in which structured patterns displayed on an electronic paper screen were concealed beneath a tissue-mimicking chicken phantom and imaged using a NIR-sensitive camera under halogen illumination. A convolutional autoencoder based on a U-Net architecture was trained on approximately 10,000 paired samples to reconstruct hidden structures from highly scattered surface images. The proposed method achieved strong reconstruction performance, with the best model reaching a peak signal-to-noise ratio (PSNR) of 20.14 dB, structural similarity index (SSIM) of 0.92, and feature similarity index (FSIM) of 0.94, significantly outperforming conventional Wiener filtering. Qualitative results demonstrated accurate recovery of subsurface shapes with minor smoothing artifacts. While generalization to out-of-distribution samples remains limited, the findings highlight the potential of combining NIR imaging and deep learning for safe, rapid, and cost-effective subsurface visualization. This work establishes a foundation for future development toward clinically relevant tumor margin detection. Full article

Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes, obscuring critical anatomical structures and compromising diagnostic precision. To address this, an unsupervised deep learning framework has been proposed for Metal Artifact Reduction (MAR) utilizing a Cycle-Consistent Adversarial Network (CycleGAN) optimized for high-fidelity restoration. Unlike supervised methods that rely on unattainable voxel-aligned paired datasets, the proposed approach leverages an unpaired dataset of approximately 4000 images, curated from the public ToothFairy dataset. The architecture integrates U-Net-based generators and PatchGAN discriminators, specifically tuned to mitigate generative hallucinations and preserve morphological integrity. Quantitative benchmarking on a held-out test set demonstrates a 34.6% improvement in the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score, a substantial reduction in Fréchet Inception Distance (FID) from 207.03 to 157.04, and a superior Structural Similarity Index Measure (SSIM) of 0.9105. The framework achieves real-time efficiency with a 3.03 ms inference time per slice, effectively suppressing artifacts while preserving anatomical detail. Expert validation confirms high fidelity; however, to ensure reliability in extreme cases, the architecture is recommended as a clinical decision-support tool under human-in-the-loop oversight. By enhancing diagnostic clarity via a scalable software pipeline, this study provides a robust solution for high-fidelity dental implant imaging. Full article