Search Results (1,608)

Background/Objectives: There is significant interest in using texture features to extract hidden image-based information. In medical imaging applications using radiomics, AI, or personalized medicine, the quest is to extract patient or disease specific information while being insensitive to other system or processing variables. While we use digital breast tomosynthesis (DBT) to show these effects, our results would be generally applicable to a wider range of other imaging modalities and applications. Methods: We examine factors in texture estimation methods, such as quantization, pixel distance offset, and region of interest (ROI) size, that influence the magnitudes of these readily computable and widely used image texture features (specifically Haralick’s gray level co-occurrence matrix (GLCM) textural features). Results: Our results indicate that quantization is the most influential of these parameters, as it controls the size of the GLCM and range of values. We propose a new multi-resolution normalization (by either fixing ROI size or pixel offset) that can significantly reduce quantization magnitude disparities. We show reduction in mean differences in feature values by orders of magnitude; for example, reducing it to 7.34% between quantizations of 8–128, while preserving trends. Conclusions: When combining images from multiple vendors in a common analysis, large variations in texture magnitudes can arise due to differences in post-processing methods like filters. We show that significant changes in GLCM magnitude variations may arise simply due to the filter type or strength. These trends can also vary based on estimation variables (like offset distance or ROI) that can further complicate analysis and robustness. We show pathways to reduce sensitivity to such variations due to estimation methods while increasing the desired sensitivity to patient-specific information such as breast density. Finally, we show that our results obtained from simulated DBT images are consistent with what we see when applied to clinical DBT images. Full article

Image super-resolution (SR) is essential for enhancing image quality in critical applications, such as medical imaging and satellite remote sensing. However, existing methods were often limited in their ability to effectively process and integrate multi-scales information from fine textures to global structures. To address these limitations, this paper proposes DSCNN, a dynamic snake convolution neural network for enhanced image super-resolution. DSCNN optimizes feature extraction and network architecture to enhance both performance and efficiency: To improve feature extraction, the core innovation is a feature extraction and enhancement module with dynamic snake convolution that dynamically adjusts the convolution kernel’s shape and position to better fit the image’s geometric structures, significantly improving feature extraction. To optimize the network’s structure, DSCNN employs an enhanced residual network framework. This framework utilizes parallel convolutional layers and a global feature fusion mechanism to further strengthen feature extraction capability and gradient flow efficiency. Additionally, the network incorporates a SwishReLU-based activation function and a multi-scale convolutional concatenation structure. This multi-scale design effectively captures both local details and global image structure, enhancing SR reconstruction. In summary, the proposed DSCNN outperforms existing methods in both objective metrics and visual perception (e.g., our method achieved optimal PSNR and SSIM results on the Set5 $\times 4$ dataset). Full article

Infrared and visible image fusion (IVIF) endeavors to amalgamate the thermal radiation characteristics from infrared images with the fine-grained texture details from visible images, aiming to produce fused outputs that are more robust and information-rich. Among the existing methodologies, those based on generative adversarial networks (GANs) have demonstrated considerable promise. However, such approaches are frequently constrained by their reliance on homogeneous discriminators possessing identical architectures, a limitation that can precipitate the emergence of undesirable artifacts in the resultant fused images. To surmount this challenge, this paper introduces HCSPNet, a novel GAN-based framework. HCSPNet distinctively incorporates heterogeneous dual discriminators, meticulously engineered for the fusion of disparate source images inherent in the IVIF task. This architectural design ensures the steadfast preservation of critical information from the source inputs, even when faced with scenarios of image degradation. Specifically, the two structurally distinct discriminators within HCSPNet are augmented with adaptive salient information distillation (ASID) modules, each uniquely structured to align with the intrinsic properties of infrared and visible images. This mechanism impels the discriminators to concentrate on pivotal components during their assessment of whether the fused image has proficiently inherited significant information from the source modalities—namely, the salient thermal signatures from infrared imagery and the detailed textural content from visible imagery—thereby markedly diminishing the occurrence of unwanted artifacts. Comprehensive experimentation conducted across multiple publicly available datasets substantiates the preeminence and generalization capabilities of HCSPNet, underscoring its significant potential for practical deployment. Additionally, we also prove that our proposed heterogeneous dual discriminators can serve as a plug-and-play structure to improve the performance of existing GAN-based methods. Full article

Background/Objectives: Deep models have achieved remarkable progress in the diagnosis of skin lesions but face two significant drawbacks. First, they cannot effectively explain the basis of their predictions. Although attention visualization tools like Grad-CAM can create heatmaps using deep features, these features often have large receptive fields, resulting in poor spatial alignment with the input image. Second, the design of most deep models neglects interpretable traditional visual features inspired by clinical experience, such as color–texture and edge features. This study aims to propose a novel approach integrating deep learning with traditional visual features to handle these limitations. Methods: We introduce the edge- and color–texture-aware bag-of-local-features model (ECT-BoFM), which limits the receptive field of deep features to a small size and incorporates edge and color–texture information from traditional features. A non-rigid reconstruction strategy ensures that traditional features enhance rather than constrain the model’s performance. Results: Experiments on the ISIC 2018 and 2019 datasets demonstrated that ECT-BoFM yields precise heatmaps and achieves high diagnostic performance, outperforming state-of-the-art methods. Furthermore, training models using only a small number of the most predictive patches identified by ECT-BoFM achieved diagnostic performance comparable to that obtained using full images, demonstrating its efficiency in exploring key clues. Conclusions: ECT-BoFM successfully combines deep learning and traditional visual features, addressing the interpretability and diagnostic accuracy challenges of existing methods. ECT-BoFM provides an interpretable and accurate framework for skin lesion diagnosis, advancing the integration of AI in dermatological research and clinical applications. Full article

Verticillium wilt is characterized by chlorosis in leaves and is a devastating disease in eggplant. Early diagnosis, prior to the manifestation of symptoms, enables targeted management of the disease. In this study, we aim to detect early leaf wilt in eggplant leaves caused by Verticillium dahliae by integrating multispectral imaging with machine learning and deep learning techniques. Multispectral and chlorophyll fluorescence images were collected from leaves of the inbred eggplant line 11-435, including data on image texture, spectral reflectance, and chlorophyll fluorescence. Subsequently, we established a multispectral data model, fusion information model, and multispectral image–information fusion model. The multispectral image–information fusion model, integrated with a two-dimensional convolutional neural network (2D-CNN), demonstrated optimal performance in classifying early-stage Verticillium wilt infection, achieving a test accuracy of 99.37%. Additionally, transfer learning enabled us to diagnose early leaf wilt in another eggplant variety, the inbred line 14-345, with an accuracy of 84.54 ± 1.82%. Compared to traditional methods that rely on visible symptom observation and typically require about 10 days to confirm infection, this study achieved early detection of Verticillium wilt as soon as the third day post-inoculation. These findings underscore the potential of the fusion model as a valuable tool for the early detection of pre-symptomatic states in infected plants, thereby offering theoretical support for in-field detection of eggplant health. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

Smoke appears earlier than flames, so image-based fire monitoring techniques mainly focus on the detection of smoke, which is regarded as one of the effective strategies for preventing the spread of initial fires that eventually evolve into serious fires. Smoke monitoring in mine fires faces serious challenges: the underground environment is complex, with smoke and backgrounds being highly integrated and visual features being blurred, which makes it difficult for existing image-based monitoring techniques to meet the actual needs in terms of accuracy and robustness. The conventional ground-based methods are directly used in the underground with a high rate of missed detection and false detection. Aiming at the core problems of mixed target and background information and high boundary uncertainty in smoke images, this paper, inspired by the principle of information entropy, proposes a method for recognizing smoke from mine fires by integrating entropy-enhanced image processing and improved YOLOv8. Firstly, according to the entropy change characteristics of spatio-temporal information brought by smoke diffusion movement, based on spatio-temporal entropy separation, an equidistant frame image differential fusion method is proposed, which effectively suppresses the low entropy background noise, enhances the detail clarity of the high entropy smoke region, and significantly improves the image signal-to-noise ratio. Further, in order to cope with the variable scale and complex texture (high information entropy) of the smoke target, an improvement mechanism based on entropy-constrained feature focusing is introduced on the basis of the YOLOv8m model, so as to more effectively capture and distinguish the rich detailed features and uncertain information of the smoke region, realizing the balanced and accurate detection of large and small smoke targets. The experiments show that the comprehensive performance of the proposed method is significantly better than the baseline model and similar algorithms, and it can meet the demand of real-time detection. Compared with YOLOv9m, YOLOv10n, and YOLOv11n, although there is a decrease in inference speed, the accuracy, recall, average detection accuracy mAP (50), and mAP (50–95) performance metrics are all substantially improved. The precision and robustness of smoke recognition in complex mine scenarios are effectively improved. Full article

Introduction: Radiomics is the extraction of non-invasive and reproducible quantitative imaging features, which may yield mineable information for clinical practice implementation. Quantification of lung function through radiomics could play a role in the management of patients with pulmonary lesions. The aim of this study is to test the capability of radiomic features to predict pulmonary function parameters, focusing on the diffusing capacity of lungs to carbon monoxide (DL_CO). Methods: Retrospective data were retrieved from electronical medical records of patients treated with Stereotactic Body Radiation Therapy (SBRT) at a single institution. Inclusion criteria were as follows: (1) SBRT treatment performed for primary early-stage non-small cell lung cancer (ES-NSCLC) or oligometastatic lung nodules, (2) availability of simulation four-dimensional computed tomography (4DCT) scan, (3) baseline spirometry data availability, (4) availability of baseline clinical data, and (5) written informed consent for the anonymized use of data. The gross tumor volume (GTV) was segmented on 4DCT reconstructed phases representing the moment of maximum inhalation and maximum exhalation (Phase 0 and Phase 50, respectively), and radiomic features were extracted from the lung parenchyma subtracting the lesion/s. An iterative algorithm was clustered based on correlation, while keeping only those most associated with baseline and post-treatment DL_CO. Three models were built to predict DL_CO abnormality: the clinical model—containing clinical information; the radiomic model—containing the radiomic score; the clinical-radiomic model—containing clinical information and the radiomic score. For the models just described, the following were constructed: Model 1 based on the features in Phase 0; Model 2 based on the features in Phase 50; Model 3 based on the difference between the two phases. The AUC was used to compare their performances. Results: A total of 98 patients met the inclusion criteria. The Charlson Comorbidity Index (CCI) scored as the clinical variable most associated with baseline DL_CO (p = 0.014), while the most associated features were mainly texture features and similar among the two phases. Clinical-radiomic models were the best at predicting both baseline and post-treatment abnormal DL_CO. In particular, the performances for the three clinical-radiomic models at predicting baseline abnormal DL_CO were AUC₁ = 0.72, AUC₂ = 0.72, and AUC₃ = 0.75, for Model 1, Model 2, and Model 3, respectively. Regarding the prediction of post-treatment abnormal DL_CO, the performances of the three clinical-radiomic models were AUC₁ = 0.91, AUC₂ = 0.91, and AUC₃ = 0.95, for Model 1, Model 2, and Model 3, respectively. Conclusions: This study demonstrates that radiomic features extracted from healthy lung parenchyma on a 4DCT scan are associated with baseline pulmonary function parameters, showing that radiomics can add a layer of information in surrogate models for lung function assessment. Preliminary results suggest the potential applicability of these models for predicting post-SBRT lung function, warranting validation in larger, prospective cohorts. Full article

This study proposes an optimized footprint recognition model based on an enhanced StarNet architecture for biometric identification in the security, medical, and criminal investigation fields. Conventional image recognition algorithms exhibit limitations in processing barefoot footprint images characterized by concentrated feature distributions and rich texture patterns. To address this, our framework integrates an improved StarNet into the backbone of YOLOv8 architecture. Leveraging the unique advantages of element-wise multiplication, the redesigned backbone efficiently maps inputs to a high-dimensional nonlinear feature space without increasing channel dimensions, achieving enhanced representational capacity with low computational latency. Subsequently, an Encoder layer facilitates feature interaction within the backbone through multi-scale feature fusion and attention mechanisms, effectively extracting rich semantic information while maintaining computational efficiency. In the feature fusion part, a feature modulation block processes multi-scale features by synergistically combining global and local information, thereby reducing redundant computations and decreasing both parameter count and computational complexity to achieve model lightweighting. Experimental evaluations on a proprietary barefoot footprint dataset demonstrate that the proposed model exhibits significant advantages in terms of parameter efficiency, recognition accuracy, and computational complexity. The number of parameters has been reduced by 0.73 million, further improving the model’s speed. Gflops has been reduced by 1.5, lowering the performance requirements for computational hardware during model deployment. Recognition accuracy has reached 99.5%, with further improvements in model precision. Future research will explore how to capture shoeprint images with complex backgrounds from shoes worn at crime scenes, aiming to further enhance the model’s recognition capabilities in more forensic scenarios. Full article

In order to address the limitations of the number of label samples in practical accurate classification scenarios and the problems of overfitting and an insufficient generalization ability caused by Few-Shot Learning (FSL) in hyperspectral image classification (HSIC), this paper designs and implements a neural architecture search (NAS) for a few-shot HSI classification method that combines meta learning. Firstly, a multi-source domain learning framework was constructed to integrate heterogeneous natural images and homogeneous remote sensing images to improve the information breadth of few-sample learning, enabling the final network to enhance its generalization ability under limited labeled samples by learning the similarity between different data sources. Secondly, by constructing precise and robust search spaces and deploying different units at different locations, the classification accuracy and model transfer robustness of the final network can be improved. This method fully utilizes spatial texture information and rich category information of multi-source data and transfers the learned meta knowledge to the optimal architecture for HSIC execution through precise and robust search space design, achieving HSIC tasks with limited samples. Experimental results have shown that our proposed method achieved an overall accuracy (OA) of 98.57%, 78.39%, and 98.74% for classification on the Pavia Center, Indian Pine, and WHU-Hi-LongKou datasets, respectively. It is fully demonstrated that utilizing spatial texture information and rich category information of multi-source data, and through precise and robust search space design, the learned meta knowledge is fully transmitted to the optimal architecture for HSIC, perfectly achieving classification tasks with few-shot samples. Full article

Single image super-resolution is the inverse problem of reconstructing a high-resolution image from its low-resolution counterpart. Although recent Transformer-based architectures leverage global context integration to improve reconstruction quality, they often overlook frequency-specific characteristics, resulting in the loss of high-frequency information. To address this limitation, we propose the Dual Frequency Adaptive Network (DFAN). DFAN first decomposes the input into low- and high-frequency components via Stationary Wavelet Transform. In the low-frequency branch, Swin Transformer layers restore global structures and color consistency. In contrast, the high-frequency branch features a dedicated module that combines Directional Convolution with Residual Dense Blocks, precisely reinforcing edges and textures. A frequency fusion module then adaptively merges these complementary features using depthwise and pointwise convolutions, achieving a balanced reconstruction. During training, we introduce a frequency-aware multi-term loss alongside the standard pixel-wise loss to explicitly encourage high-frequency preservation. Extensive experiments on the Set5, Set14, BSD100, Urban100, and Manga109 benchmarks show that DFAN achieves up to +0.64 dBpeak signal-to-noise ratio, +0.01 structural similarity index measure, and −0.01learned perceptual image patch similarity over the strongest frequency-domain baselines, while also delivering visibly sharper textures and cleaner edges. By unifying spatial and frequency-domain advantages, DFAN effectively mitigates high-frequency degradation and enhances SISR performance. Full article

In recent years, the rapid advancement of deep learning techniques has significantly propelled the development of face forgery methods, drawing considerable attention to face forgery detection. However, existing detection methods still struggle with generalization across different datasets and forgery techniques. In this work, we address this challenge by leveraging both local texture cues and global frequency domain information in a complementary manner to enhance the robustness of face forgery detection. Specifically, we introduce a local texture mining and enhancement module. The input image is segmented into patches and a subset is strategically masked, then texture enhanced. This joint masking and enhancement strategy forces the model to focus on generalizable localized texture traces, mitigates overfitting to specific identity features and enabling the model to capture more meaningful subtle traces of forgery. Additionally, we extract multi-scale frequency domain features from the face image using wavelet transform, thereby preserving various frequency domain characteristics of the image. And we propose an innovative frequency-domain processing strategy to adjust the contributions of different frequency-domain components through frequency-domain selection and dynamic weighting. This Facilitates the model’s ability to uncover frequency-domain inconsistencies across various global frequency layers. Furthermore, we propose an integrated framework that combines these two feature modalities, enhanced with spatial attention and channel attention mechanisms, to foster a synergistic effect. Extensive experiments conducted on several benchmark datasets demonstrate that the proposed technique demonstrates superior performance and generalization capabilities compared to existing methods. Full article

Single-image super-resolution (SISR) plays a critical role in enhancing visual quality for real-world applications, including industrial inspection and embedded vision systems. While deep learning-based approaches have made significant progress in SR, existing lightweight SR models often fail to accurately reconstruct high-frequency textures, especially under complex degradation scenarios, resulting in blurry edges and structural artifacts. To address this challenge, we propose a Dense Residual Fused Attention Network (DRFAN), a novel lightweight hybrid architecture designed to enhance high-frequency texture recovery in challenging degradation conditions. Moreover, by coupling convolutional layers and attention mechanisms through gated interaction modules, the DRFAN enhances local details and global dependencies with linear computational complexity, enabling the efficient utilization of multi-level spatial information while effectively alleviating the loss of high-frequency texture details. To evaluate its effectiveness, we conducted ×4 super-resolution experiments on five public benchmarks. The DRFAN achieves the best performance among all compared lightweight models. Visual comparisons show that the DRFAN restores more accurate geometric structures, with up to +1.2 dB/+0.0281 SSIM gain over SwinIR-S on Urban100 samples. Additionally, on a domain-specific rice grain dataset, the DRFAN outperforms SwinIR-S by +0.19 dB in PSNR and +0.0015 in SSIM, restoring clearer textures and grain boundaries essential for industrial quality inspection. The proposed method provides a compelling balance between model complexity and image reconstruction fidelity, making it well-suited for deployment in resource-constrained visual systems and industrial applications. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

Accurate estimation of rice leaf nitrogen content (LNC) is essential for optimizing nitrogen management in precision agriculture. However, challenges such as spectral saturation and canopy structural variations across different growth stages complicate this task. This study proposes a robust framework for LNC estimation that integrates both spectral and texture features extracted from UAV-based multispectral imagery through the development of novel Spectral–Texture Fusion Indices (STFIs). Field data were collected under nitrogen gradient treatments across three critical growth stages: heading, early filling, and late filling. A total of 18 vegetation indices (VIs), 40 texture features (TFs), and 27 STFIs were derived from UAV images. To optimize the feature set, a two-stage feature selection strategy was employed, combining Pearson correlation analysis with model-specific embedded selection methods: Recursive Feature Elimination with Cross-Validation (RFECV) for Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and Sequential Forward Selection (SFS) for Support Vector Regression (SVR) and Deep Neural Networks (DNNs). The models—RFECV-RF, RFECV-XGBoost, SFS-SVR, and SFS-DNN—were evaluated using four feature configurations. The SFS-DNN model with STFIs achieved the highest prediction accuracy (R² = 0.874, RMSE = 2.621 mg/g). SHAP analysis revealed the significant contribution of STFIs to model predictions, underscoring the effectiveness of integrating spectral and texture information. The proposed STFI-based framework demonstrates strong generalization across phenological stages and offers a scalable, interpretable approach for UAV-based nitrogen monitoring in rice production systems. Full article