Search Results (316)

Timely and accurate diagnosis of gastrointestinal diseases (GIDs) remains a critical bottleneck in clinical endoscopy, particularly due to the limited contrast and sensitivity of conventional white light imaging (WLI) in detecting early-stage mucosal abnormalities. To overcome this, this research presents Spectrum Aided Vision Enhancer (SAVE), an innovative, software-driven framework that transforms standard WLI into high-fidelity hyperspectral imaging (HSI) and simulated narrow-band imaging (NBI) without any hardware modification. SAVE leverages advanced spectral reconstruction techniques, including Macbeth Color Checker-based calibration, principal component analysis (PCA), and multivariate polynomial regression, achieving a root mean square error (RMSE) of 0.056 and structural similarity index (SSIM) exceeding 90%. Trained and validated on the Kvasir v2 dataset (n = 6490) using deep learning models like ResNet-50, ResNet-101, EfficientNet-B2, both EfficientNet-B5 and EfficientNetV2-B0 were used to assess diagnostic performance across six key GI conditions. Results demonstrated that SAVE enhanced imagery and consistently outperformed raw WLI across precision, recall, and F1-score metrics, with EfficientNet-B2 and EfficientNetV2-B0 achieving the highest classification accuracy. Notably, this performance gain was achieved without the need for specialized imaging hardware. These findings highlight SAVE as a transformative solution for augmenting GI diagnostics, with the potential to significantly improve early detection, streamline clinical workflows, and broaden access to advanced imaging especially in resource constrained settings. Full article

Grains and their derivatives play a crucial role as staple foods for the global population. Identifying grains in the food chain that are free from mycotoxin contamination is essential. Researchers have explored various traditional detection methods to address this concern. However, as grain consumption becomes increasingly time-sensitive and dynamic, traditional approaches face growing limitations. In recent years, emerging techniques—particularly molecular-based vibrational spectroscopy methods such as visible–near-infrared (Vis–NIR), near-infrared (NIR), Raman, mid-infrared (MIR) spectroscopy, and hyperspectral imaging (HSI)—have been applied to assess fungal contamination in grains and their products. This review summarizes research advances and applications of vibrational spectroscopy in detecting mycotoxins in grains from 2019 to 2025. The fundamentals of their work, information acquisition characteristics and their applicability in food matrices were outlined. The findings indicate that vibrational spectroscopy techniques can serve as valuable tools for identifying fungal contamination risks during the production, transportation, and storage of grains and related products, with each technique suited to specific applications. Given the close link between grain-based foods and humans, future efforts should further enhance the practicality of vibrational spectroscopy by simultaneously optimizing spectral analysis strategies across multiple aspects, including chemometrics, model transfer, and data-driven artificial intelligence. Full article

Pesticide residues in fruits and vegetables pose a serious threat to food safety. Traditional detection methods have defects such as complex operation, high cost, and long detection time. Therefore, it is of great significance to develop rapid, non-destructive, and efficient detection technologies and equipment. In recent years, the combination of spectroscopic techniques and imaging technologies with machine learning algorithms has developed rapidly, providing a new attempt to solve this problem. This review focuses on the research progress of the combination of spectroscopic techniques (near-infrared spectroscopy (NIRS), hyperspectral imaging technology (HSI), surface-enhanced Raman scattering (SERS), laser-induced breakdown spectroscopy (LIBS), and imaging techniques (visible light (VIS) imaging, NIRS imaging, HSI technology, terahertz imaging) with machine learning algorithms in the detection of pesticide residues in fruits and vegetables. It also explores the huge challenges faced by the application of spectroscopic and imaging technologies combined with machine learning algorithms in the intelligent perception of pesticide residues in fruits and vegetables: the performance of machine learning models requires further enhancement, the fusion of imaging and spectral data presents technical difficulties, and the commercialization of hardware devices remains underdeveloped. This review has proposed an innovative method that integrates spectral and image data, enhancing the accuracy of pesticide residue detection through the construction of interpretable machine learning algorithms, and providing support for the intelligent sensing and analysis of agricultural and food products. Full article

Hyperspectral imaging (HSI) plays a pivotal role in modern agriculture by capturing fine-grained spectral signatures that support crop classification, health assessment, and land-use monitoring. However, the transition from raw spectral data to reliable semantic understanding remains challenging—particularly under fragmented planting patterns, spectral ambiguity, and spatial heterogeneity. To address these limitations, we propose UniHSFormer-X, a unified transformer-based framework that reconstructs agricultural semantics through prototype-guided token routing and hierarchical context modeling. Unlike conventional models that treat spectral–spatial features uniformly, UniHSFormer-X dynamically modulates information flow based on class-aware affinities, enabling precise delineation of field boundaries and robust recognition of spectrally entangled crop types. Evaluated on three UAV-based benchmarks—WHU-Hi-LongKou, HanChuan, and HongHu—the model achieves up to 99.80% overall accuracy and 99.28% average accuracy, outperforming state-of-the-art CNN, ViT, and hybrid architectures across both structured and heterogeneous agricultural scenarios. Ablation studies further reveal the critical role of semantic routing and prototype projection in stabilizing model behavior, while parameter surface analysis demonstrates consistent generalization across diverse configurations. Beyond high performance, UniHSFormer-X offers a semantically interpretable architecture that adapts to the spatial logic and compositional nuance of agricultural imagery, representing a forward step toward robust and scalable crop classification. Full article

Hyperspectral imaging (HSI) is a powerful tool for precision imaging tasks such as vegetation analysis, but its widespread use remains limited due to the high cost of equipment and challenges in data acquisition. To explore a more accessible alternative, we propose a Green Normalized Difference Vegetation Index (GNDVI)-guided green channel adjustment method, termed G-RGB, which enables the estimation of near-infrared (NIR) reflectance from standard RGB image inputs. The G-RGB method enhances the green channel to encode NIR-like information, generating a spectrally enriched representation. Building on this, we introduce FUSE-Net, a novel deep learning model that combines multi-scale convolutional layers and MLP-Mixer-based channel learning to effectively model spatial and spectral dependencies. For evaluation, we constructed a high-resolution RGB-HSI paired dataset by capturing basil leaves under controlled conditions. Through ablation studies and band combination analysis, we assessed the model’s ability to recover spectral information. The experimental results showed that the G-RGB input consistently outperformed unmodified RGB across multiple metrics, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), spectral correlation coefficient (SCC), and structural similarity (SSIM), with the best performance observed when paired with FUSE-Net. While our method does not replace true NIR data, it offers a viable approximation during inference when only RGB images are available, supporting cost-effective analysis in scenarios where HSI systems are inaccessible. Full article

Oat is a highly nutritious cereal crop, and the moisture content of its seeds plays a vital role in cultivation management, storage preservation, and quality control. To enable efficient and non-destructive prediction of this key quality parameter, this study presents a modeling framework integrating hyperspectral imaging (HSI) technology with a dual-optimization machine learning strategy. Seven spectral preprocessing techniques—standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative (FD), second derivative (SD), and combinations such as SNV + FD, SNV + SD, and SNV + MSC—were systematically evaluated. Among them, SNV combined with FD was identified as the optimal preprocessing scheme, effectively enhancing spectral feature expression. To further refine the predictive model, three feature selection methods—successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and principal component analysis (PCA)—were assessed. PCA exhibited superior performance in information compression and modeling stability. Subsequently, a dual-optimized neural network model, termed Bayes-ASFSSA-BP, was developed by incorporating Bayesian optimization and the Adaptive Spiral Flight Sparrow Search Algorithm (ASFSSA). Bayesian optimization was used for global tuning of network structural parameters, while ASFSSA was applied to fine-tune the initial weights and thresholds, improving convergence efficiency and predictive accuracy. The proposed Bayes-ASFSSA-BP model achieved determination coefficients (R²) of 0.982 and 0.963, and root mean square errors (RMSEs) of 0.173 and 0.188 on the training and test sets, respectively. The corresponding mean absolute error (MAE) on the test set was 0.170, indicating excellent average prediction accuracy. These results significantly outperformed benchmark models such as SSA-BP, ASFSSA-BP, and Bayes-BP. Compared to the conventional BP model, the proposed approach increased the test R² by 0.046 and reduced the RMSE by 0.157. Moreover, the model produced the narrowest 95% confidence intervals for test set performance (Rp²: [0.961, 0.971]; RMSE: [0.185, 0.193]), demonstrating outstanding robustness and generalization capability. Although the model incurred a slightly higher computational cost (480.9 s), the accuracy gain was deemed worthwhile. In conclusion, the proposed Bayes-ASFSSA-BP framework shows strong potential for accurate and stable non-destructive prediction of oat seed moisture content. This work provides a practical and efficient solution for quality assessment in agricultural products and highlights the promise of integrating Bayesian optimization with ASFSSA in modeling high-dimensional spectral data. Full article

This paper proposes an experimental procedure based on hyperspectral imaging (HSI) combined with statistical classification for assessing archaeo-paleoanthropological stratigraphic deposits at the Gran Dolina site (TD10 unit), located in the Sierra de Atapuerca (Burgos, Spain). Representative spectral reflectance signatures were determined and analyzed using HSI measurements and statistical classification methods in natural light conditions across various capture distances. This study aims to characterize and quantify cave sediments by defining spectral models for feature classification and spectral similarity analysis, evaluating the strengths and limitations of spectral captures at this specific site. HSI technology enhances the analysis and identification of materials at an internationally recognized reference site for human evolution studies. Hyperspectral imaging assessment of archaeo-paleoanthropological stratigraphic deposits emerges as an innovative digital tool, revolutionizing the sustainable management of cultural heritage and environmental sciences by enabling advanced material identification and stratigraphic analysis. Full article

The accurate identification of water bodies in hyperspectral images (HSIs) remains challenging due to hierarchical representation imbalances in deep learning models, where shallow layers overly focus on spectral features, boundary ambiguities caused by the relatively low spatial resolution of satellite imagery, and limited detection capability for small-scale aquatic features such as narrow rivers. To address these challenges, this study proposes Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evaluation (HASSDE-NAS). The architecture integrates three specialized units; a spectral-aware dynamic band selection cell suppresses redundant spectral bands, while a geometry-enhanced edge attention cell refines fragmented spatial boundaries. Additionally, a bidirectional fusion alignment cell jointly optimizes spectral and spatial dependencies. A heuristic cell search algorithm optimizes the network architecture through architecture stability, feature diversity, and gradient sensitivity analysis, which improves search efficiency and model robustness. Evaluated on the Gaofen-5 datasets from the Guangdong and Henan regions, HASSDE-NAS achieves overall accuracies of 92.61% and 96%, respectively. This approach outperforms existing methods in delineating narrow river systems and resolving water bodies with weak spectral contrast under complex backgrounds, such as vegetation or cloud shadows. By adaptively prioritizing task-relevant features, the framework provides an interpretable solution for hydrological monitoring and advances neural architecture search in intelligent remote sensing. Full article

Hyperspectral imaging (HSI) has broad applications for detecting the soluble solids content (SSC) of fruits. This study explores the integration of HSI with machine learning and deep learning to predict SSC in two mandarin varieties: Ponkan and Tianchao. Traditional machine learning models (support vector machines and partial least squares regression) and deep learning models (convolutional neural networks, long short-term memory, and Transformer architectures) were evaluated for SSC prediction performance. Combined models that integrated different deep learning architectures were also explored. Results revealed varietal differences in prediction performance. For Ponkan mandarins, the best SSC prediction model was achieved by partial least squares regression, outperforming deep learning models. In contrast, for Tianchao mandarins, the deep learning model based on convolutional neural network slightly surpassed the traditional model. SHapley Additive exPlanations (SHAP) analysis indicated that the influential wavelengths varied between varieties, suggesting differences in key spectral features for SSC prediction. These findings highlight the potential of combining HSI with advanced modeling for citrus SSC prediction, while emphasizing the need for variety-specific models. Future research should focus on developing more robust and generalized prediction models by incorporating a broader range of citrus varieties and exploring the impact of varietal characteristics on model performance. Full article

Hyperspectral imaging (HSI) is an effective technique for material identification and classification, utilizing spectral signatures with applications in remote sensing, environmental monitoring, and allied disciplines. Despite its potential, the broader adoption of HSI technology is hindered by challenges related to compactness, affordability, and durability, exacerbated by the absence of standardized protocols for developing practical hyperspectral cameras. This study introduces a comprehensive framework for developing a compact, cost-effective, and robust hyperspectral camera, employing commercial off-the-shelf (COTS) components and a volume phase holographic (VPH) grism. The use of COTS components reduces development time and manufacturing costs while maintaining adequate performance, thereby improving accessibility for researchers and engineers. The incorporation of a VPH grism enables an on-axis optical design, enhancing compactness, reducing alignment sensitivity, and improving system robustness. The proposed framework encompasses spectrograph design, including optical simulations and tolerance analysis conducted in ZEMAX OpticStudio, alongside assembly procedures, performance assessment, and hyperspectral image acquisition via a pushbroom scanning approach, all integrated into a structured, step-by-step workflow. The resulting prototype, housed in an aluminum enclosure, operates within the 420–830 nm wavelength range, achieving a spectral resolution of 2 nm across 205 spectral bands. It effectively differentiates vegetation, water, and built structures, resolves atmospheric absorption features, and demonstrates the ability to distinguish materials in low-light conditions, providing a scalable and practical advancement in HSI technology. Full article

Benefiting from the development of deep learning, the super-resolution technology for remote sensing hyperspectral images (HSIs) has achieved impressive progress. However, due to the high coupling of complex components in remote sensing HSIs, it is challenging to achieve a complete characterization of the internal information, which in turn limits the precise reconstruction of detailed texture and spectral features. Therefore, we propose the multi-attitude hybrid network (MAHN) for extracting and characterizing information from multiple feature spaces. On the one hand, we construct the spectral hypergraph cross-attention module (SHCAM) and the spatial hypergraph self-attention module (SHSAM) based on the high and low-frequency features in the spectral and the spatial domains, respectively, which are used to capture the main structure and detail changes within the image. On the other hand, high-level semantic information in mixed pixels is parsed by spectral mixture analysis, and semantic hypergraph 3D module (SH3M) are constructed based on the abundance of each category to enhance the propagation and reconstruction of semantic information. Furthermore, to mitigate the domain discrepancies among features, we introduce a sensitive bands attention mechanism (SBAM) to enhance the cross-guidance and fusion of multi-domain features. Extensive experiments demonstrate that our method achieves optimal reconstruction results compared to other state-of-the-art algorithms while effectively reducing the computational complexity. Full article

Geographical origins and varietal characteristics can significantly affect the quality of Citri Reticulatae Pericarpium (Chenpi), making rapid and accurate identification essential for consumer protection. To overcome the inefficiency and high cost of conventional detection methods, this study proposed a nondestructive approach that integrates hyperspectral imaging (HSI) with deep learning to classify Chenpi varieties and their geographical origins. Hyperspectral data were collected from 15 Chenpi varieties (citrus peel) across 13 major production regions in China using three dataset configurations: exocarp-facing-upward (Z), endocarp-facing-upward (F), and a fused dataset combining random orientations (ZF). Convolutional neural networks (CNNs) were developed and compared with conventional machine learning models, including partial least-squares discriminant analysis (PLS-DA), support vector machines (SVMs), and a multilayer perceptron (MLP). The CNN model achieved 96.39% accuracy for varietal classification with the ZF dataset, while the Z-PLSDA model optimized with second derivative (D2) preprocessing and competitive adaptive reweighted sampling (CARS) feature selection attained 91.67% accuracy in geographical origin discrimination. Feature wavelength selection strategies, such as CARS, simplified the model complexity while maintaining a classification performance comparable to that of the full-spectrum models. These findings demonstrated that HSI combined with deep learning could provide a rapid, nondestructive, and cost-effective solution for Chenpi quality assessment and origin traceability. Full article

A majority of hyperspectral super-resolution methods aim to enhance the spatial resolution of hyperspectral imaging data (HSI) by integrating high-resolution multispectral imaging data (MSI), leveraging rich spectral information for various geospatial applications. Key challenges include spectral distortions from high-frequency spatial data, high computational complexity, and limited training data, particularly for new-generation sensors with unique noise patterns. In this contribution, we propose a novel parallel patch-wise sparse residual learning (P²SR) algorithm for resolution enhancement based on fusion of HSI and MSI. The proposed method uses multi-decomposition techniques (i.e., Independent component analysis, Non-negative matrix factorization, and 3D wavelet transforms) to extract spatial and spectral features to form a sparse dictionary. The spectral and spatial characteristics of the scene encoded in the dictionary enable reconstruction through a first-order optimization algorithm to ensure an efficient sparse representation. The final spatially enhanced HSI is reconstructed by combining the learned features from low-resolution HSI and applying an MSI-regulated guided filter to enhance spatial fidelity while minimizing artifacts. P²SR is deployable on a high-performance computing (HPC) system with parallel processing, ensuring scalability and computational efficiency for large HSI datasets. Extensive evaluations on three diverse study sites demonstrate that P²SR consistently outperforms traditional and state-of-the-art (SOA) methods in both quantitative metrics and qualitative spatial assessments. Specifically, P²SR achieved the best average PSNR (25.2100) and SAM (12.4542) scores, indicating superior spatio-spectral reconstruction contributing to sharper spatial features, reduced mixed pixels, and enhanced geological features. P²SR also achieved the best average ERGAS (8.9295) and Q2n (0.5156), which suggests better overall fidelity across all bands and perceptual accuracy with the least spectral distortions. Importantly, we show that P²SR preserves critical spectral signatures, such as Fe²⁺ absorption, and improves the detection of fine-scale environmental and geological structures. P²SR’s ability to maintain spectral fidelity while enhancing spatial detail makes it a powerful tool for high-precision remote sensing applications, including mineral mapping, land-use analysis, and environmental monitoring. Full article

Marine steel structures face severe corrosion risks due to harsh environmental conditions, posing significant logistical, economic, and safety challenges for inspection and maintenance. Traditional corrosion assessment methods are costly, labor-intensive, and potentially hazardous. This study evaluated the capabilities of visible-to-near-infrared hyperspectral imaging (HSI) for automating corrosion detection and severity classification in steel samples subjected to accelerated corrosion conditions simulating marine exposure. Marine steel coupons were partially coated to simulate protective paint and immersed in natural brackish water from the Panama Canal, creating varying corrosion levels. Hyperspectral images were acquired in controlled illumination conditions, calibrated radiometrically, and reduced in dimensionality via principal component analysis (PCA). Four machine learning models, including k-nearest neighbors, support vector machine, random forest, and multilayer perceptron, were tested for classifying corrosion severity. The multilayer perceptron achieved the highest accuracy at 96.18%, clearly distinguishing among five defined corrosion stages. These findings demonstrate that hyperspectral imaging, coupled with machine learning techniques, provides a viable, accurate, non-destructive methodology for assessing marine steel corrosion, potentially reducing costs, improving safety, and streamlining maintenance procedures. Full article

Hyperspectral remote sensing is crucial due to its continuous spectral information, especially in the quantitative remote sensing (QRS) field. Surface reflectance (SR), a fundamental product in QRS, can play a pivotal role in application accuracy and serves as a key indicator of sensor performance. However, the distinctive spectral characteristics of a hyperspectral image (HSI) make it particularly susceptible to noise during the process of imaging, which inevitably degrades data quality and reduces SR accuracy. Moreover, the validation of hyperspectral SR faces challenges due to the scarcity of reliable validation data. To address these issues, aiming at fast and efficient processing of Chinese domestic ZY1-02D hyperspectral level-1 data, this study proposes a comprehensive processing framework: (1) To address the low efficiency of traditional bad line detection by visual examination, an automatic bad line detection method based on the pixel grayscale gradient threshold algorithm is proposed; (2) A spectral correlation-based interpolation method is developed to overcome the poor performance of adjacent-column averaging in repairing wide bad lines; (3) A reliable validation method was established based on the spectral band adjustment factors method to compare hyperspectral SR with multispectral SR and in-situ ground measurements. The results and analysis demonstrate that the proposed method improves the accuracy of ZY1-02D SR and the method ensures high processing efficiency, requiring only 5 min per scene of ZY1-02D HSI. This study provides a technical foundation for the application of ZY1-02D HSIs and offers valuable insights for the development and enhancement of next-generation hyperspectral sensors. Full article