Search Results (406)

Due to diverse lighting conditions and photo environments, shadows are almost ubiquitous in images, especially document images captured with mobile devices. Shadows not only seriously affect the visual quality and readability of a document but also significantly hinder image processing. Although shadow removal research has achieved good results in natural scenes, specific studies on document images are lacking. To effectively remove shadows in document images, the dark illumination correction network is proposed, which mainly consists of two modules: shadow detection and illumination correction. First, a simplified shadow-corrected attention block is designed to combine spatial and channel attention, which is used to extract the features, detect the shadow mask, and correct the illumination. Then, the shadow detection block detects shadow intensity and outputs a soft shadow mask to determine the probability of each pixel belonging to shadow. Lastly, the illumination correction block corrects dark illumination with a soft shadow mask and outputs a shadow-free document image. Our experiments on five datasets show that the proposed method achieved state-of-the-art results, proving the effectiveness of illumination correction. Full article

The Mazenod Lake region of the southern Great Bear Magmatic Zone (GBMZ) of the Northwest Territories, Canada, comprises the north-central portion of the Faber volcano-plutonic belt. Widespread and abundant surface exposure of several coalescing hydrothermal systems enables this paper to document, without ambiguity, the relationships between geology, structure, alteration, and mineralization in this well exposed iron-oxide–copper–gold (IOCG) mineral system. Mazenod geology comprises rhyodacite to basaltic-andesite ignimbrite sheets with interlayered volcaniclastic sedimentary rocks dominated by fine-grained laminated tuff sequences. Much of the intermediate to mafic nature of volcanic rocks is masked by low-intensity but pervasive metasomatism. The region is affected by a series of coalescing magmatic–hydrothermal systems that host the Sue–Dianne magnetite–hematite IOCG deposit and several related showings including magnetite, skarn, and iron oxide apatite (IOA) styles of alteration ± mineralization. The mid to upper levels of these systems are exposed at surface, with underlying batholith, pluton and stocks exposed along the periphery, as well as locally within volcanic rocks associated with more intense alteration and mineralization. Widespread alteration includes potassic and sodic metasomatism, and silicification with structurally controlled giant quartz complexes. Localized tourmaline, skarn, magnetite–actinolite, and iron-oxide alteration occur within structural breccias, and where most intense formed the Sue–Dianne Cu-Ag-Au diatreme-like breccia deposit. Magmatism, volcanism, hydrothermal alteration, and mineralization formed during a negative tectonic inversion within the Wopmay Orogen. This generated a series of oblique offset rifted basins with continental style arc magmatism and extensional structures unique to GBMZ rifting. All significant hydrothermal centers in the Mazenod region occur along and at the intersections of crustal faults either unique to or put under tension during the GBMZ inversion. Full article

Short-term precipitation forecasting is a core task in meteorological science, aiming to achieve accurate predictions by modeling the spatiotemporal evolution of radar echo sequences, thereby supporting meteorological services and disaster warning systems. However, existing spatiotemporal sequence prediction methods still struggle to disentangle complex spatiotemporal dependencies effectively and fail to capture the nonlinear chaotic characteristics of precipitation systems. This often results in ambiguous predictions, attenuation of echo intensity, and spatial localization errors. To address these challenges, this paper proposes a unified spatiotemporal sequence prediction framework based on spatiotemporal masking, which comprises two stages: self-supervised pre-training and task-oriented fine-tuning. During pre-training, the model learns global structural features of meteorological systems from sparse contexts by randomly masking local spatiotemporal regions of radar images. In the fine-tuning stage, considering the importance of the temporal dimension in short-term precipitation forecasting and the complex long-range dependencies in spatiotemporal evolution of precipitation systems, we design an RNN-based cyclic temporal mask self-encoder model (MAE-RNN) and a transformer-based spatiotemporal attention model (STMT). The former focuses on capturing short-term temporal dynamics, while the latter simultaneously models long-range dependencies across space and time via a self-attention mechanism, thereby avoiding the smoothing effects on high-frequency details that are typical of conventional convolutional or recurrent structures. The experimental results show that STMT improves 3.73% and 2.39% in CSI and HSS key indexes compared with the existing advanced models, and generates radar echo sequences that are closer to the real data in terms of air mass morphology evolution and reflection intensity grading. Full article

The accurate classification of cocoa pod ripeness is critical for optimizing harvest timing, improving post-harvest processing, and ensuring consistent quality in chocolate production. Traditional ripeness assessment methods are often subjective, labor-intensive, or destructive, highlighting the need for automated, non-invasive solutions. This study evaluates the performance of R-CNN-based deep learning models—Faster R-CNN and Mask R-CNN—for the detection and segmentation of cocoa pods across four ripening stages (0–2 months, 2–4 months, 4–6 months, and >6 months) using the RipSetCocoaCNCH12 dataset, which is publicly accessible, comprising 4116 labeled images collected under real-world field conditions, in the context of precision agriculture. Initial experiments using pretrained weights and standard configurations on a custom COCO-format dataset yielded promising baseline results. Faster R-CNN achieved a mean average precision (mAP) of 64.15%, while Mask R-CNN reached 60.81%, with the highest per-class precision in mature pods (C4) but weaker detection in early stages (C1). To improve model robustness, the dataset was subsequently augmented and balanced, followed by targeted hyperparameter optimization for both architectures. The refined models were then benchmarked against state-of-the-art YOLOv8 networks (YOLOv8x and YOLOv8l-seg). Results showed that YOLOv8x achieved the highest mAP of 86.36%, outperforming YOLOv8l-seg (83.85%), Mask R-CNN (73.20%), and Faster R-CNN (67.75%) in overall detection accuracy. However, the R-CNN models offered valuable instance-level segmentation insights, particularly in complex backgrounds. Furthermore, a qualitative evaluation using confidence heatmaps and error analysis revealed that R-CNN architectures occasionally missed small or partially occluded pods. These findings highlight the complementary strengths of region-based and real-time detectors in precision agriculture and emphasize the need for class-specific enhancements and interpretability tools in real-world deployments. Full article

The article presents a three-stage methodology for calibrating 3D printing using mSLA technology, aimed at improving dimensional accuracy and print repeatability. The proposed approach is based on procedures that enable the collection and analysis of numerical data, thereby minimizing the influence of the operator’s subjective judgment, which is commonly relied upon in traditional calibration methods. In the first stage, compensation for the uneven illumination of the LCD matrix was performed by establishing a regression model that describes the relationship between UV radiation intensity and pixel brightness. Based on this model, a grayscale correction mask was developed. The second stage focused on determining the optimal exposure time, based on its effect on dimensional accuracy, detail reproduction, and model strength. The optimal exposure time is defined as the duration that provides the highest possible mechanical strength without significant loss of detail due to the light bleed phenomenon (i.e., diffusion of UV radiation beyond the mask edge). In the third stage, scale correction was applied to compensate for shrinkage and geometric distortions, further reducing the impact of light bleed on the dimensional fidelity of printed components. The proposed methodology was validated using an Anycubic Photon M3 Premium printer with Anycubic ABS-Like Resin Pro 2.0. Compensating for light intensity variation reduced the original standard deviation from 0.26 to 0.17 mW/cm², corresponding to a decrease of more than one third. The methodology reduced surface displacement due to shrinkage from 0.044% to 0.003%, and the residual internal dimensional error from 0.159 mm to 0.017 mm (a 72% reduction). Full article

Privacy-preserving record linkage (PPRL) aims to link records from different data sources while ensuring sensitive information is not disclosed. Utilizing blockchain as a trusted third party is an effective strategy for enhancing transparency and auditability in PPRL. However, to ensure data privacy during computation, such approaches often require computationally intensive cryptographic techniques. This can introduce significant computational overhead, limiting the method’s efficiency and scalability. To address this performance bottleneck, we combine blockchain with the distributed computation of secret sharing to propose a PPRL method based on blockchain-coordinated distributed computation. At its core, the approach utilizes Bloom filters to encode data and employs Boolean and arithmetic secret sharing to decompose the data into secret shares, which are uploaded to the InterPlanetary File System (IPFS). Combined with masking and random permutation mechanisms, it enhances privacy protection. Computing nodes perform similarity calculations locally, interacting with IPFS only a limited number of times, effectively reducing communication overhead. Furthermore, blockchain manages the entire computation process through smart contracts, ensuring transparency and correctness of the computation, achieving efficient and secure record linkage. Experimental results demonstrate that this method effectively safeguards data privacy while exhibiting high linkage quality and scalability. Full article

Under the background of globalization and the latest technological changes, many enterprises ensure corporate competitiveness and sustainable development by deploying production globalization and transforming production modes. This paper proposes a task-based enterprise model to study how enterprises’ production mode transformation toward intelligent manufacturing affects corporate offshoring production. Intelligent manufacturing forms relative push–pull forces on corporate offshoring production through reshoring effects and offshoring effects on the extensive margin of task sets while promoting corporate offshoring production through productivity effects on the intensive margin. Empirically, this paper constructs a staggered quasi-natural experiment using China’s Intelligent Manufacturing Pilot Demonstration Projects (IMPDP), adopts the heterogeneity-robust nonlinear Difference-in-Differences (DID) method, and confirms that intelligent manufacturing has significant positive causal effects on Chinese manufacturing enterprises’ offshoring production. The reshoring effect of intelligent manufacturing is stronger than the offshoring effect, but its powerful productivity effect masks the reshoring effect in overall empirical results. The positive effects of intelligent manufacturing are more significant in non-state-owned enterprises (non-SOEs) and capital-intensive enterprises. Further considering host country selection for corporate offshoring, this study finds that intelligent manufacturing simultaneously promotes corporate offshoring production to both developed and developing countries, but enterprises prefer Belt and Road Initiative countries. Additionally, intelligent manufacturing also promotes corporate offshore trade activities while causing the reshoring of offshore R&D activities. Overall, the transition of production modes toward intelligent manufacturing in Chinese manufacturing enterprises generally leads to a further expansion of corporate offshoring production. Full article

The urban heat island (UHI) effect and its associated extreme weather events have adverse impacts on human environment-coupled systems. However, the spatiotemporal variations in the UHI effect, as well as potential influencing factors, across climate zones remain poorly understood. This study explored how climate zones influenced the spatiotemporal variation in, trends in, and drivers of summer daytime surface UHI intensity (SUHII) in 220 Chinese cities located in five climate zones from 2000 to 2020. SUHII was quantified using MODIS land surface temperature (LST) data and remote sensing-derived urban built-up area masks were used to quantify SUHII. The Mann–Kendall test was applied to detect long-term SUHII trends, while Pearson correlation and stepwise multiple regression analyses were performed to identify key climatic and geographic drivers across different climate zones. The results indicated summer daytime SUHII values of 1.75 °C ± 1.19 °C, 1.74 °C ± 0.81 °C, 2.37 °C ± 0.75 °C, 2.14 °C ± 1.00 °C, and 2.36 °C ± 0.91 °C for the middle temperate zone (MTZ), south temperate zone (STZ), north subtropical zone (NSZ), middle subtropical zone (MSZ), and south subtropical zone (SSZ), respectively. In most cities, the SUHII increased significantly over time (p < 0.05). Pearson’s correlation analysis indicated that the enhanced vegetation index (EVI) and net radiation (NR) were moderately correlated with the SUHII in the MTZ, with correlation coefficients (r) of 0.465 and 0.42 (p < 0.05). Using a multivariate stepwise regression model, the relative contributions of various influencing factors to the UHI effect were quantified, explaining 27.1% to 57.2% of the variation across different climate zones. In particular, the economic vulnerability index and population density were the main factors affecting the SUHII in the MTZ and SSZ. Our findings support the development of policies aimed at mitigating the UHI effect by addressing the specific requirements of different climate zones to reduce. Full article

Many researchers focus on improving reproductive health in sows and ensuring successful breeding by accurately identifying the optimal time of ovulation through estrus detection. One promising non-contact technique involves using computer vision to analyze temperature variations in thermal images of the sow’s vulva. However, variations in camera distance during dataset collection can significantly affect the accuracy of this method, as different distances alter the resolution of the region of interest, causing pixel intensity values to represent varying areas and temperatures. This inconsistency hinders the detection of the subtle temperature differences required to distinguish between estrus and non-estrus states. Moreover, failure to maintain a consistent camera distance, along with external factors such as atmospheric conditions and improper calibration, can distort temperature readings, further compromising data accuracy and reliability. Furthermore, without addressing distance variations, the model’s generalizability diminishes, increasing the likelihood of false positives and negatives and ultimately reducing the effectiveness of estrus detection. In our previously proposed methodology for estrus detection in sows, we utilized YOLOv8 for segmentation and keypoint detection, while monocular depth estimation was used for camera calibration. This calibration helps establish a functional relationship between the measurements in the image (such as distances between labia, the clitoris-to-perineum distance, and vulva perimeter) and the depth distance to the camera, enabling accurate adjustments and calibration for our analysis. Estrus classification is performed by comparing new data points with reference datasets using a three-nearest-neighbor voting system. In this paper, we aim to enhance our previous method by incorporating the mean pixel intensity of the region of interest as an additional factor. We propose a detailed four-step methodology coupled with two stages of evaluation. First, we carefully annotate masks around the vulva to calculate its perimeter precisely. Leveraging the advantages of deep learning, we train a model on these annotated images, enabling segmentation using the cutting-edge YOLOv9 algorithm. This segmentation enables the detection of the sow’s vulva, allowing for analysis of its shape and facilitating the calculation of the mean pixel intensity in the region. Crucially, we use monocular depth estimation from the previous method, establishing a functional link between pixel intensity and the distance to the camera, ensuring accuracy in our analysis. We then introduce a classification approach that differentiates between estrus and non-estrus regions based on the mean pixel intensity of the vulva. This classification method involves calculating Euclidean distances between new data points and reference points from two datasets: one for “estrus” and the other for “non-estrus”. The classification process identifies the five closest neighbors from the datasets and applies a majority voting system to determine the label. A new point is classified as “estrus” if the majority of its nearest neighbors are labeled as estrus; otherwise, it is classified as “non-estrus”. This automated approach offers a robust solution for accurate estrus detection. To validate our method, we propose two evaluation stages: first, a quantitative analysis comparing the performance of our new YOLOv9 segmentation model with the older U-Net and YOLOv8 models. Secondly, we assess the classification process by defining a confusion matrix and comparing the results of our previous method, which used the three nearest points, with those of our new model that utilizes five nearest points. This comparison allows us to evaluate the improvements in accuracy and performance achieved with the updated model. The automation of this vital process holds the potential to revolutionize reproductive health management in agriculture, boosting breeding success rates. Through thorough evaluation and experimentation, our research highlights the transformative power of computer vision, pushing forward more advanced practices in the field. Full article

Urbanization has emerged as a significant driver of environmental change, particularly impacting local climates through the creation of urban heat islands (SUHIs). SUHIs, characterized by higher temperatures in urban or metropolitan areas than in their rural surroundings, have become a critical focus of urban climate studies. This study aims to examine the spatial and temporal dynamics of both thermal and vegetative indices (BT, LST, NDVI, NDBI, BUI, ECI, SUHI, UTFVI) across different land cover types in Samsun, Türkiye, in order to assess their contribution to the urban heat island effect. Specifically, brightness temperature (BT), land surface temperature (LST), normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), built-up index (BUI), environmental condition index (ECI), urban heat island (SUHI) intensity, and urban thermal field variance index (UTFVI) were calculated and assessed. The analysis utilized cloud-free Landsat 8 imagery sourced from the US Geological Survey via the Google Earth Engine platform, employing a one-year median for each pixel using a cloud masking algorithm. Land use and land cover (LULC) classification was conducted using the random forest (RF) algorithm with satellite composite imagery, achieving an overall accuracy of 85% for 2014 and 86% for 2023. This study provides a detailed analysis of the effects of various land use and cover types on temperature, vegetation, and structural characteristics, revealing the role of changes in different land types on the urban heat island effect. In the LULC classification, water bodies consistently maintained low LST values below 23 °C for both years, while built-up land exhibited the greatest temperature increase, from approximately 25 °C in 2014 to more than 31 °C in 2023. The analysis also revealed that LST varies with the size and type of vegetation, with a mean LST differential between all green spaces and urban areas averaging 7–8 °C, and differences reaching 12 °C in industrial zones. Full article

Automatic segmentation of nuclei on breast cancer histology images is a basic and important step for diagnosis in a computer-aided diagnostic approach and helps pathologists discover cancer early. Nuclei segmentation remains a challenging problem due to cancer biology and the variability of tissue characteristics; thus, their detection in an image is a very tedious and time-consuming task. In this context, overlapping nuclei objects present difficulties in separating them by conventional segmentation methods; thus, active contours can be employed in image segmentation. A major limitation of the active contours method is its inability to resolve image boundaries/edges of intersecting objects and segment multiple overlapping objects as a single object. Therefore, we present a hybrid active contour (connected component + active contours) method to segment cancerous lesions in unsupervised human breast histology images. Initially, this approach prepares and pre-processes data through various augmentation methods to increase the dataset size. Then, a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, morphology operation techniques, namely erosion, dilation, opening, and distance transform, are used to highlight foreground and background pixels while removing overlapping regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and assigns them to their relevant labeled component to form a binary mask. Once all binary-masked groups have been determined, a deep-learning recurrent neural network (RNN) model from the Keras architecture uses this information to automatically segment nuclei objects having cancerous lesions on the image via the active contours method. This approach, therefore, uses the capabilities of connected components analysis to solve the limitations of the active contour method. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 15,179 images. This proposed method produced a significant evaluation result of $98.71\%$ accuracy score. Full article

Pneumothorax is a critical condition that requires rapid and accurate diagnosis from standard chest radiographs. Identifying and segmenting the location of the pneumothorax are essential for developing an effective treatment plan. nnUNet is a self-configuring, deep learning-based framework for medical image segmentation. Despite adjusting its parameters automatically through data-driven optimization strategies and offering robust feature extraction and segmentation capabilities across diverse datasets, our initial experiments revealed that nnUNet alone struggled to achieve consistently accurate segmentation for pneumothorax, particularly in challenging scenarios where subtle intensity variations and anatomical noise obscure the target regions. This study aims to enhance the accuracy and robustness of pneumothorax segmentation in low-contrast chest radiographs by integrating spatial prior information and attention mechanism into the nnUNet framework. In this study, we introduce the spatial prior contrast adapter (SPCA)-enhanced nnUNet by implementing two modules. First, we integrate an SPCA utilizing the MedSAM foundation model to incorporate spatial prior information of the lung region, effectively guiding the segmentation network to focus on anatomically relevant areas. In the meantime, a probabilistic atlas, which shows the probability of an area prone to pneumothorax, is generated based on the ground truth masks. Both the lung segmentation results and the probabilistic atlas are used as attention maps in nnUNet. Second, we combine the two attention maps as additional input into nnUNet and integrate an attention mechanism into standard nnUNet by using a convolutional block attention module (CBAM). We validate our method by experimenting on the dataset CANDID-PTX, a benchmark dataset representing 19,237 chest radiographs. By introducing spatial awareness and intensity adjustments, the model reduces false positives and improves the precision of boundary delineations, ultimately overcoming many of the limitations associated with low-contrast radiographs. Compared with standard nnUNet, SPCA-enhanced nnUNet achieves an average Dice coefficient of 0.81, which indicates an improvement of standard nnUNet by 15%. This study provides a novel approach toward enhancing the segmentation performance of pneumothorax with low contrast in chest X-ray radiographs. Full article

The detection of voids in pavement infrastructure is essential for road safety and efficient maintenance. Traditional methods of analyzing ground-penetrating radar (GPR) data are labor-intensive and error-prone. This study presents a novel approach using the EfficientDet-D3 deep learning model for automated void detection in GPR images. The model combines advanced feature extraction and compound scaling to balance accuracy and computational efficiency, making it suitable for real-time applications. A diverse GPR image dataset, including various pavement types and environmental conditions, was curated and preprocessed to improve model generalization. The model was fine-tuned through hyperparameter optimization, achieving a precision of 91.2%, a recall of 87.5%, and an F1-score of 89.3%. It also attained mean Average Precision (mAP) values of 89.7% at IoU 0.5 and 84.3% at IoU 0.75, demonstrating strong localization performance. Comparative analysis with models such as YOLOv8 and Mask R-CNN shows that EfficientDet-D3 offers a superior balance between accuracy and inference speed, with an inference time of 68 ms. This research provides a scalable, efficient solution for pavement void detection, paving the way for integrating deep learning models into pavement management systems to enhance infrastructure sustainability. Future work will focus on model optimization and expanding dataset diversity. Full article

Medical image segmentation, especially in chest X-ray (CXR) analysis, encounters substantial problems such as class imbalance, annotation inconsistencies, and the necessity for accurate pathological region identification. This research aims to improve the precision and clinical reliability of pulmonary abnormality segmentation by developing NCT-CXR, a framework that combines anatomically constrained data augmentation with expert-guided annotation refinement. NCT-CXR applies carefully calibrated discrete-angle rotations (±5°, ±10°) and intensity-based augmentations to enrich training data while preserving spatial and anatomical integrity. To address label noise in the NIH Chest X-ray dataset, we further introduce a clinically validated annotation refinement pipeline using the OncoDocAI platform, resulting in multi-label pixel-level segmentation masks for nine thoracic conditions. YOLOv8 was selected as the segmentation backbone due to its architectural efficiency, speed, and high spatial accuracy. Experimental results show that NCT-CXR significantly improves segmentation precision, especially for pneumothorax (0.829 and 0.804 for ±5° and ±10°, respectively). Non-parametric statistical testing (Kruskal–Wallis, H = 14.874, p = 0.0019) and post hoc Nemenyi analysis (p = 0.0138 and p = 0.0056) confirm the superiority of discrete-angle augmentation over mixed strategies. These findings underscore the importance of clinically constrained augmentation and high-quality annotation in building robust segmentation models. NCT-CXR offers a practical, high-performance solution for integrating deep learning into radiological workflows. Full article

Chili pepper (Capsicum annuum L.), a globally important economic crop, faces production challenges characterized by high labor intensity, cost, and inefficiency. Intelligent technologies offer key opportunities for sector transformation. This review begins by outlining the diversity of major chili pepper cultivars, differences in key quality indicators, and the resulting specific harvesting needs. It then reviews recent progress in intelligent perception, recognition, and automation within the chili pepper industry. For perception and recognition, the review covers the evolution from traditional image processing to deep learning-based methods (e.g., YOLO and Mask R-CNN achieving a mAP > 90% in specific studies) for pepper detection, segmentation, and fine-grained cultivar identification, analyzing the performance and optimization in complex environments. In terms of automation, we systematically discuss the principles and feasibility of different mechanized harvesting machines, consider the potential of vision-based keypoint detection for the point localization of picking, and explore motion planning and control for harvesting robots (e.g., robotic systems incorporating diverse end-effectors like soft grippers or cutting mechanisms and motion planning algorithms such as RRT) as well as seed cleaning/separation techniques and simulations (e.g., CFD and DEM) for equipment optimization. The main current research challenges are listed including the environmental adaptability/robustness, efficiency/real-time performance, multi-cultivar adaptability/flexibility, system integration, and cost-effectiveness. Finally, future directions are given (e.g., multimodal sensor fusion, lightweight models, and edge computing applications) in the hope of guiding the intelligent growth of the chili pepper industry. Full article