Search Results (1,567)

Diabetic retinopathy (DR) is a leading cause of vision impairment and permanent blindness worldwide, requiring accurate and automated systems for multi-grade severity classification. However, standard Convolutional Neural Networks (CNNs) often struggle to capture fine, high-frequency microvascular patterns critical for diagnosis. This study proposes a Robust Intelligent CNN Model (RICNN) that integrates Gabor-based feature extraction with deep learning to improve DR classification. Specifically, Gabor filters are applied during preprocessing to extract orientation- and frequency-sensitive texture features, which are transformed into feature maps and concatenated with CNN feature representations at the fully connected layer (feature-level fusion). The model also incorporates the Synthetic Minority Oversampling Technique (SMOTE) for data balancing and the Adam optimizer for efficient convergence. This integration enhances sensitivity to microvascular structures such as microaneurysms and hemorrhages. The proposed RICNN was evaluated on the Messidor dataset (1200 images) across four severity levels: Mild, Moderate, Severe, and Proliferative DR. The model achieved an accuracy of 89%, a precision of 88.75%, a recall of 89%, and an F1-score of 89%, with AUCs of 97% for Severe DR and 99% for Proliferative DR. Comparative analysis confirms that the proposed texture-aware Gabor enhancement significantly outperforms LBP and Color Histogram approaches, indicating its potential for reliable clinical decision support. Full article

Underwater images often suffer from mixed degradations, including motion blur, which reduce structural clarity and adversely affect downstream vision tasks. To address this problem, we propose a physically guided Transformer framework for underwater motion deblurring. The proposed method combines two-stage cepstrum-based blur estimation with a point spread function (PSF)-guided self-attention mechanism. Specifically, blur parameters are first robustly estimated through cepstrum analysis, ellipse fitting, and negative-peak refinement, and the resulting PSF is then embedded into the Transformer attention module to guide feature aggregation. On the real underwater benchmark datasets UIEB Challenge-60 and EUVP330, the proposed method achieves UIQM/UCIQE scores of 4.09/0.56 and 3.40/0.58, respectively, significantly outperforming UFPNet and Phaseformer, thereby demonstrating superior perceptual restoration in terms of sharpness, contrast, and color consistency. On the synthetic test set, the proposed method attains 24.23 dB PSNR and 0.918 SSIM, outperforming both recent deep models and classical non-blind deconvolution methods, which confirms its strong restoration fidelity and structural consistency. In the controlled water-tank experiments, the proposed method consistently achieves the best performance under different camera motion speeds, demonstrating excellent robustness and practical applicability. Overall, the proposed framework provides an effective and physically interpretable solution for underwater motion deblurring. Full article

To support low-cost, non-destructive crop growth monitoring, this study systematically compared different vegetation indices, voxel sizes, and camera angles using a point cloud voxelization approach combined with a vegetation index weighted canopy volume index (CVM_VI) to assess aboveground biomass (AGB) in winter oilseed rape (Brassica napus L.). Field experiments were conducted from 2021 to 2024 at the Yangma Experimental Base of the Chengdu Academy of Agricultural and Forestry Sciences. Red, green, blue (RGB) imagery of oilseed rape was acquired using an unmanned aerial vehicle (UAV) during the following five key growth stages: seedling, bolting, flowering, podding, and maturity. Collected images were processed to generate point clouds, which were subsequently voxelized at four resolutions (0.03, 0.05, 0.07, and 0.1 m). CVM_VI was constructed by integrating vegetation indices (VIs) derived from the RGB data and the voxelized canopy structural information. Regression models were established between the CVM_VI values and field-measured AGB to estimate biomass. Model performance was evaluated using the coefficient of determination (R²), root mean square error (RMSE), and relative error (RE). There were strong correlations (r > 0.80) between the estimated and measured AGB across all voxelization treatments throughout the growth period. Among the 20 VIs tested, regression methods based on the blue green ratio index (BGI), color intensity index, blue red ratio index, vegetative index, and green red ratio index consistently showed superior estimation performance across three consecutive years, demonstrating their good applicability for estimating AGB in oilseed rape under varying agronomic conditions (different varieties, densities, and sowing dates). The cubic regression model CVM_BGI performed best under a 45° UAV camera angle, with the highest R² and lowest RMSE and RE (2021–2022: R² = 0.864, RMSE = 2414.18 kg/ha, RE = 14.8%; 2022–2023: R² = 0.754, RMSE = 2550.53 kg/ha, RE = 14.9%; 2023–2024: R² = 0.863, RMSE = 1953.61 kg/ha, RE = 22.9%). Since the estimation performance showed negligible differences among voxel sizes, and the 0.1–m voxel offered the smallest data volume and shortest analysis time, the CVM_BGI model with a 0.1–m voxel was selected as the preferred approach, providing a practical balance between estimation performance and processing demand. These findings highlight the application potential of point cloud voxelization technology for crop biomass estimation. This study proposes a novel, non-destructive, and efficient framework for estimating field crop AGB using low-cost UAV RGB imagery, facilitating the wider adoption of UAV technology in practical agricultural production. Full article

While convolutional neural networks (CNNs) excel at image classification, their generalization across domains and robustness to nonlinear degradation remain challenges in art media classification (AMC). To address these challenges, this article presents a dual-stage analytical framework: first, an evaluation of seven discrete CNN architectures—ranging from VGG16 to ConvNeXt—subjected to domain shift using the New Spain (Mexico) Art Media Dataset; and second, a formal robustness analysis using an artistic corruption benchmark (Art-C). This benchmark simulates nonlinear degradations, including cracking, oxidized varnish, and pictorial abstraction. Our results demonstrate that while deep convolutional representations maintain acceptable transferability (accuracy $>70\%$), significant variability exists in architectural stability (mean 0.0607) under progressive stochastic degradation. Notably, Xception exhibited the highest robustness (Art-mCE = 0.8039), whereas VGG16 showed the greatest relative performance decay. Severity analysis further indicates that structural perturbations induce higher error rates than chromatic shifts, suggesting that CNNs are more sensitive to topological features (depth and residual connections) than color-space distributions. We provide quantitative evidence characterizing the relationship between architectural topology and empirical stability in non-natural image domains. Full article

Addressing the challenges of complex background interference, low lighting conditions, small target recognition, and difficulty in maturity grading in the automated detection of Pleurotus ostreatus, this study proposes a lightweight improved scheme based on color feature enhancement. By collecting 4779 images from five developmental stages in three typical planting environments, including greenhouses and mushroom houses, an HSV hue analysis database was established to determine key hue intervals [4°, 38°] or [110°, 155°] for different environments. Secondly, based on the hue interval distribution of Pleu-rotus ostreatus, YOLOv13 was used as the base model, with the addition of an HSV hue mask as the fourth channel to improve the input layer. The custom ColorWeight module was used to enhance color feature expression; the hypergraph computation module was improved to enhance feature correlation; and the neck network incorporated the StockenAttention module to improve the ability to capture maturity features. The accuracy of the improved model was increased to 89.5% in mAP@0.5 (+3.3%), surpassing the mainstream YOLOv8n-12n series. Efficiency optimization achieved real-time detection at 12.58 FPS on the RTX3090Ti platform. In practical applications, the accuracy of maturity recognition was significantly improved, with a 73.6% decrease in the misclassification rate of maturity and a reduction in missed detections, achieving an F1 score of 0.91. In conclusion, through the deep integration of Hue features and deep learning models, while ensuring lightweight deployment (with only a 10.5% increase in parameter count), the accuracy and practicality of Pleurotus ostreatus detection were significantly improved, providing an effective solution for intelligent mushroom house management. Full article

The carbonate massifs of the southern Italian Apennines host extensive karst aquifers, which represent the principal drinking water resources. This study focuses on the Dragone Plain polje, a vast closed karst depression located in the main recharge sector of the Terminio–Tuoro carbonate massif. The polje drains a ~55 km² endorheic catchment and may be flooded during the cold and wet season, forming a temporary lake. We employed continuous hydroclimatic time series (rainfall, groundwater level, spring discharge, and river level) together with sparse Sentinel-2 true color satellite images for the period 2020–2024 to analyze the flooding process in the polje and its hydraulic connection with the saturated zone of the karst aquifer. Results indicate that lake formation depends on the balance among soil moisture, rainfall intensity, and runoff development, which were modeled on a daily scale. Daily recharge was also estimated and compared with groundwater level time series from the deep karst aquifer. The modeling was integrated with cross-correlation analysis of the time series, providing insights into the propagation of precipitation pulses through the hydrogeological system. This case study represents an important example for understanding the relationship between karst polje hydrological functioning and climate in a Mediterranean area. Full article

Background/Objectives: Brain death determination in children is clinically challenging. When standard clinical examination cannot be completed or reliably interpreted, ancillary testing is required—yet many established methods depend on infrastructure or patient transport that may not be feasible in critically ill pediatric patients. Orbital ultrasonography is bedside-applicable and non-invasive, but remains poorly characterized in children. Methods: We conducted a single-center retrospective study of 28 pediatric patients evaluated for suspected brain death between January 2021 and February 2025. Patients were classified as brain death-positive [BD(+), n = 20] or brain death-negative [BD(−), n = 8] based on clinical criteria independent of imaging findings. Orbital color Doppler parameters (ophthalmic artery, central retinal artery, posterior ciliary artery) and optic nerve sheath diameter (ONSD) were measured under a standardized protocol by a single experienced operator. Ophthalmic artery resistive index (OA-RI) was defined a priori as the primary outcome; ONSD was the secondary outcome. Group comparisons used the Mann–Whitney U test with Cliff’s delta effect sizes; false discovery rate correction was applied to secondary and exploratory comparisons. ROC analyses were performed to assess discriminative performance. The study was reported in accordance with the STARD 2015 guidelines for diagnostic accuracy research. Results: OA-RI was markedly higher in BD(+) patients (0.84 [IQR 0.80–0.90] vs. 0.65 [0.58–0.69]; p < 0.001; δ = 0.975). ROC analysis yielded an AUC of 0.99 (95% CI: 0.96–1.00); at a cut-off of ≥0.77, sensitivity was 95.0% and specificity 100.0%. ONSD also differed significantly between groups (4.75 [4.15–5.08] mm vs. 3.90 [3.40–4.15] mm; p = 0.012; δ = 0.619; AUC = 0.81, 95% CI: 0.62–1.00; cut-off ≥ 4.2 mm; sensitivity and specificity both 75.0%). Across all three orbital vessels, end-diastolic velocity was consistently reduced and resistive indices elevated in BD(+) patients. Systolic velocities did not differ meaningfully between groups. Cut-off values represent cohort-specific statistical optima and should be interpreted as exploratory. Conclusions: Orbital Doppler ultrasonography demonstrates a coherent high-resistance hemodynamic pattern in pediatric brain death. OA-RI showed strong discriminative performance and may serve as a useful bedside adjunct in selected cases where ancillary testing is indicated. ONSD provides complementary anatomical evidence. These findings are exploratory and require prospective validation in larger, multicenter pediatric cohorts. Full article

Turbid Class II inland waters such as Taihu Lake exhibit a “spectral uplift” effect driven by suspended particulate matter (SPM) scattering and colored dissolved organic matter (CDOM) absorption, which can obscure chlorophyll-a (Chl-a) signals in the visible–red-edge region and challenge retrieval under small-sample, collinear feature settings. Using multispectral observations from the BC-1A satellite (carrying the Lightweight Hyperspectral Remote Sensing Imager, LHRSI) and synchronous satellite–ground in situ measurements acquired over Taihu Lake in late autumn, this study proposes Chl-a-oriented PCA–RF (COP-RF), a leakage-safe inversion framework integrating correlation screening, principal component analysis (PCA), and random forest (RF) regression. Candidate band-combination features are generated, and PCA is applied for orthogonal compression to mitigate collinearity before RF learning. A stratified five-fold cross-validation based on Chl-a quantile bins is adopted, with screening, standardization, and PCA fitted only on training folds. COP-RF achieves stable performance under the current dataset ($R^2=0.671$, RMSE $=1.80\mathsf{\mu }$g/L, MAE $=1.25\mathsf{\mu }$g/L). Spatial inversion shows higher Chl-a near shores and bays and lower values in the lake center, consistent with Sentinel-2 hotspot ranks. Full article

Stain variability in digital pathology affects both cross-center diagnostic consistency and the robustness of downstream computational analysis. In this work, we formulate stain normalization as a variational inverse problem and derive a Screened Poisson Normalization (SPN) model from the steady-state reaction–diffusion mechanism underlying histological staining. In the CIE $L^{*}{a}^{*}{b}^{*}$ space, the model couples a gradient-domain fidelity term with a chromatic anchoring term, yielding a screened Poisson equation that preserves tissue morphology while enforcing color consistency. We prove that the corresponding variational problem is well-posed in $H^1\left(\mathsf{\Omega }\right)$ and stable with respect to perturbations of the input data. We further show that the screening term induces an intrinsic localization length ${𝓁}_c\sim {\lambda }_c^{-1/2}$, so that boundary perturbations decay exponentially away from tile interfaces. Based on this locality, we develop a non-overlapping tiled DCT-based spectral solver for gigapixel whole-slide images, enabling consistent tile-wise stain normalization and seamless whole-slide reassembly without heuristic boundary blending. Experiments on multi-scanner, multi-protocol, and archival-fading pathology datasets show that SPN achieves stable stain normalization with competitive chromatic alignment and strong preservation of diagnostically relevant microstructure, particularly in full-slide and tiled reconstruction settings. Supplementary experiments on synthetic pathology-like images further support the robustness of SPN under controlled color perturbations and indicate good generalization across diverse staining variations. Full article

Background: Intravascular lithotripsy (IVL) has emerged as a novel vessel preparation device for patients with peripheral artery disease undergoing angioplasty. The IVL catheter includes an integrated balloon, which emits high pressure and transient sonic waves. The release of shockwaves results in cracking of intimal and medial calcium within the vessel wall improving lumen patency. Objectives: The aim of this prospective observational cohort study is to evaluate the morphological and imaging changes in atherosclerotic plaque in patients with PAD undergoing IVL as a vessel preparation technique, followed by angioplasty with drug-coated balloon (DCB) or stent placement if required. Secondary endpoint is to evaluate the efficacy of IVL in the perfusion of the lower extremities, by calculating the ankle–brachial index (ABI) and toe–brachial index (TBI) post-angioplasty, as well as adverse events within 30 days. Methods: Consecutive adult (≥18 years of age) patients with symptomatic femoropopliteal artery disease selected to undergo IVL will be included in the study. Computed tomography angiography (CTA) of the lower limbs will be performed pre- and postoperatively. Intraoperatively, an intravascular ultrasound (IVUS) will be used before and immediately post-angioplasty, for real-time evaluation of the morphological and quantitative changes in the atherosclerotic plaque. All participants will be clinically re-evaluated in 30 days postoperatively and a color Duplex ultrasound of the lower extremity arteries will be performed. The perfusion of the peripheral arteries will be assessed using ABI and TBI post-procedurally. Outcomes: The primary outcome is the quantitative assessment of changes in plaque morphology and volume within the index target lesion, based on pre- and post-procedural computed tomography angiography using TeraRecon™ (Durham, NC, USA) plaque analysis module, reflecting plaque modification and redistribution, in the context of IVL-based vessel preparation. Secondary outcomes include improvement of peripheral arterial perfusion and freedom from clinically driven target lesion revascularization (CD-TLR) and major adverse events. Full article

Drones have proven effective for acquiring aerial imagery, and when equipped with onboard analysis tools, they can automatically identify objects of interest. Neural-network methods for image analysis typically require large training datasets and substantial computational resources. By contrast, algorithmic techniques can detect objects using simple features, such as pixel colors, thereby reducing the need for extensive training and computational resources. Once trained, both types of system can analyze images in a short time. In our experiments, each approach has distinct strengths. The YOLO-based detector is more accurate for complex-shaped objects, such as trees, whereas the pixel-color approach performs better on sparser objects. This paper proposes YOLO-C3, a hybrid system designed for onboard drone image processing. By leveraging the strengths of both YOLO-based and pixel-based approaches, YOLO-C3 balances detection accuracy with estimation confidence. Trained on Mediterranean imagery dataset, the system is optimized for identifying natural objects, including citrus groves and trees. To assess the robustness of the image classifier, a K-fold cross-validation is performed. Compared to existing models, YOLO-C3 detects a wider range of natural objects with high accuracy and minimal latency, achieving a processing speed of 0.01 s per image. By performing object detection locally, drones can adapt their trajectories to support emergency response, helping to map safe corridors and locate buildings where people may be awaiting rescue after a natural disaster. Full article

Parameters of reflected light, measured in narrow or broad spectral bands, are widely analyzed for remote and proximal sensing of plant responses to stressors. Specifically, parameters of reflectance in red (R), green (G), and blue (B) spectral bands measured using simple color images can be sensitive to characteristics of plants. The conventional view is that RGB reflectance primarily reveals long-term changes in plants (days, weeks, etc.). In this study, we investigated light-induced changes in RGB reflectance in wheat (Triticum aestivum L.) and pea (Pisum sativum L.) leaves. Illumination increased this reflectance for about 10 min in wheat and about 15–20 min in pea; these changes relaxed after light intensity was decreased. The changes in RGB reflectance were strongly related to the effective quantum yield of photosystem II and non-photochemical quenching of chlorophyll fluorescence under high light intensity; these relations were absent under low light intensity. We hypothesized that changes in both RGB reflectance and photosynthetic parameters were related to the light-induced changes in chloroplast localization. A simple mathematical model of optical properties and photosynthesis in leaves was developed; results of the model-based analysis supported the proposed hypothesis. Experimental analysis of the dynamics of light transmittance additionally supported this hypothesis. Our results thus show that RGB imaging can be sensitive to fast changes in plants. Full article

This paper presents a method for measuring the spatial distribution of surface normal vectors with high angular accuracy. The measured data are visualized using a color-mapping technique and represented as normal maps, which are commonly used in computer graphics. Reliable methods for evaluating material surface properties have long been sought in industrial applications where visual assessments of reflective properties are still widely employed, particularly in appearance-critical fields. Motivated by this need, we introduce an imaging-based technique for measuring the high-resolution spatial distribution of surface normal vectors from specular reflection. A dedicated measurement apparatus was developed to capture surface normal vectors at 1024 × 1024 sampling points with a spatial resolution of 0.02 × 0.02 mm and an angular resolution of approximately 0.1°. Using this apparatus, normal maps were obtained for various materials, including plastic, ceramic tile, inkjet paper, and aluminum sheets. The spatial distribution of surface normal vectors reflects surface roughness, which strongly influences perceived texture. The resulting normal maps enable not only quantitative surface analysis for industrial inspection but also the physical reproduction of gloss in computer graphics. Full article

Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift. Full article

Sol–gel-based optical functional sensor coatings were developed for real-time monitoring of multiphase saponification reactions in microreactors. Various pH-sensitive indicator mixtures, including bromocresol green and bromocresol purple (BCG and BCP) and methyl red–methyl orange, were incorporated into sol–gel coatings and evaluated on test plates across pH range of 2–12. Coatings with BCG and BCP 1:3 demonstrated the most pronounced color change at high pH (11–12), with distinct hue (H) transitions providing a reliable measure of local pH. These optimized coatings were integrated into microreactor channels to track the passage of oil and NaOH slugs under varying flow rates. Hue analysis produced reproducible plateaus corresponding to NaOH-rich (H = 50°) and oil-rich (H = 41°) phases, enabling droplet-level resolution of slug flow and detection of flow-regime transitions. The sensor response was fully reversible, highlighting the robustness and reusability of the coatings. Unlike previous high-resolution fluorescence-based systems, this approach relies on simple visible-light imaging and low-cost data extraction, leaving the reaction chemistry unaltered. The results demonstrate that sol–gel coatings coupled with hue-based analysis provide a practical, noninvasive, and real-time monitoring strategy for multiphase reactions in microreactors, with potential for implementation in industrial or IoT-enabled process control systems. Full article