Search Results (17,632)

Image analysis is becoming increasingly popular in many industries. Its use is perfect for, among other things, assessing the quality of products on or off the production line. Highly automated, high-performance systems can be used for this purpose. However, there are situations in which automated vision systems cannot be used on the production line due to the specific nature of the process. One such situation is testing the resistance of paint applied to glass when washing in automatic dishwashers. It is carried out outside the production line, and typical production vision systems are not used here. An attempt was made to develop a cheap and easy-to-implement research method enabling quantitative measurement of paint loss on glass when testing the coating’s resistance to automatic washing. For this purpose, analysis of images taken during the study was carried out. The developed method is based on taking a series of photos of the tested object between each stage of the wash resistance test. The obtained photographic material is then analyzed by measuring the size of paint losses expressed in the number of pixels. Then, the percentage of paint loss is calculated. This method is cheap to implement and highly accurate. Statistical analysis of the results confirmed the method’s accuracy at 98%. Full article

This study investigates the sociodemographic and contextual determinants influencing Internet usage among individuals with visual impairments in Thailand, contributing to the literature on the digital disability divide. Data from the “Disability Survey 2022” conducted by the National Statistical Office of Thailand were used. Descriptive statistics, chi-square tests, and logistic regression analysis were performed on data from 5621 visually impaired respondents. The findings indicate that approximately 26.88% of individuals with visual impairments use the Internet. The logistic regression analysis highlights several critical disparities. Males exhibit lower odds of Internet use compared with females (adjusted odds ratio [AOR] = 0.850, p = 0.034). Younger individuals are more likely to use the Internet; a decline in use was observed with increasing age (AOR for 60+ years = 0.052, p < 0.001). Regional disparities are evident. Individuals from the northeastern (AOR = 2.044, p < 0.001), central (AOR = 1.356, p < 0.008), and southern (AOR = 1.992, p < 0.001) regions showed higher odds of Internet use compared with those from the northern region. Higher income (AOR for 5000–9999 THB = 1.798, p = 0.001), educational attainment (AOR for bachelor’s degree = 14.915, p < 0.001), and wealth index (AOR for wealthy = 5.034, p < 0.001) increase the likelihood of Internet use. Employed individuals are more likely to use the Internet (AOR = 3.159, p < 0.001) compared with unemployed individuals. Additionally, the severity of the visual impairment is crucial, with those having low vision in both eyes more likely to engage online than those who are completely blind in both eyes (AOR = 5.935, p < 0.001). These findings highlight the need for comprehensive digital inclusion initiatives that address various factors, including age-inclusive digital literacy programs, targeted regional infrastructure development, economic support to improve digital access, and advancements in assistive technologies. This study provides valuable insights for policymakers in Thailand and other developing countries, enhancing the understanding of the digital disability divide and informing strategies to foster greater digital equity. Full article

Mobility, a vital part of daily life, significantly impacts human well-being. Understanding this relationship is crucial for shaping the future trajectory of mobility, a connection often overlooked in previous research. This study explores the complex relationship between mobility and well-being and proposes a holistic framework for mobility’s future, prioritizing individual and societal well-being. The motivation for this research stems from the growing need to balance technological advancements in transportation with the well-being of diverse populations, especially as the mobility landscape evolves with innovations like autonomous vehicles and intelligent mobility solutions. We employ bibliometric methods, analyzing 53,588 academic articles to identify key themes and research trends related to mobility and well-being. This study categorizes these articles into thematic clusters using the Louvain modularity maximization algorithm, which facilitates the formation of cohesive groups based on citation patterns. Our findings underline the significant impact of mobility on physical, mental, psychological, financial, and social well-being. The proposed framework features four pillars: vehicle, infrastructure and environment, mobility stakeholders, and policy. This framework underscores the importance of collaboration between institutional and individual actions in shaping a future mobility landscape that is technologically advanced, socially responsible, and conducive to an improved quality of life. Full article

Camouflaged object detection (COD) is a challenging task that involves identifying objects that closely resemble their background. In order to detect camouflaged objects more accurately, we propose a diffusion model for the COD network called DMNet. DMNet formulates COD as a denoising diffusion process from noisy boxes to prediction boxes. During the training stage, random boxes diffuse from ground-truth boxes, and DMNet learns to reverse this process. In the sampling stage, DMNet progressively refines random boxes to prediction boxes. In addition, due to the camouflaged object’s blurred appearance and the low contrast between it and the background, the feature extraction stage of the network is challenging. Firstly, we proposed a parallel fusion module (PFM) to enhance the information extracted from the backbone. Then, we designed a progressive feature pyramid network (PFPN) for feature fusion, in which the upsample adaptive spatial fusion module (UAF) balances the different feature information by assigning weights to different layers. Finally, a location refinement module (LRM) is constructed to make DMNet pay attention to the boundary details. We compared DMNet with other classical object-detection models on the COD10K dataset. Experimental results indicated that DMNet outperformed others, achieving optimal effects across six evaluation metrics and significantly enhancing detection accuracy. Full article

microRNAs (miRNAs) are promising biomarkers for many diseases, including multiple sclerosis (MS). The neurofilament light chain (NfL) is a biomarker that can detect axonal damage in different neurological diseases. The objective of this study was to evaluate the association of the expression profile of pre-selected miRNAs and NfL levels with clinical and radiological variables in MS patients. We conducted a 1-year longitudinal prospective study in MS patients with different clinical forms. We measured clinical disability using the expanded disability status scale (EDSS), the magnetic resonance imaging (MRI) volumetry baseline, and cognitive functioning using the processing speed test (PST) at baseline and 1 year later. Selected serum miRNAs and serum NfL (sNfL) levels were quantified. Seventy-three patients were recruited. MiR-126.3p correlated with EDSS and cognitive status at baseline and miR-126.3p and miR-9p correlated with cognitive deterioration at 1 year. Correlations with regional brain volumes were observed between miR-126.3p and the cortical gray matter, cerebellum, putamen, and pallidum; miR-146a.5p with the cerebellum and pallidum; miR-29b.3p with white matter and the pallidum; miR-138.5p with the pallidum; and miR-9.5p with the thalamus. sNfL was correlated with miR-9.5p. miR-146a.5p was also associated with the MS phenotype. These data justify future studies to further explore the utility of miRNAs (mirR-126.3p, miR-146.5p, and miR.9-5p) and sNfL levels as biomarkers of MS. Full article

The task of localizing distinct anatomical structures in medical image data is an essential prerequisite for several medical applications, such as treatment planning in orthodontics, bone-age estimation, or initialization of segmentation methods in automated image analysis tools. Currently, Anatomical Landmark Localization (ALL) is mainly solved by deep-learning methods, which cannot guarantee robust ALL predictions; there may always be outlier predictions that are far from their ground truth locations due to out-of-distribution inputs. However, these localization outliers are detrimental to the performance of subsequent medical applications that rely on ALL results. The current ALL literature relies heavily on implicit anatomical constraints built into the loss function and network architecture to reduce the risk of anatomically infeasible predictions. However, we argue that in medical imaging, where images are generally acquired in a controlled environment, we should use stronger explicit anatomical constraints to reduce the number of outliers as much as possible. Therefore, we propose the end-to-end trainable Global Anatomical Feasibility Filter and Analysis (GAFFA) method, which uses prior anatomical knowledge estimated from data to explicitly enforce anatomical constraints. GAFFA refines the initial localization results of a U-Net by approximately solving a Markov Random Field (MRF) with a single iteration of the sum-product algorithm in a differentiable manner. Our experiments demonstrate that GAFFA outperforms all other landmark refinement methods investigated in our framework. Moreover, we show that GAFFA is more robust to large outliers than state-of-the-art methods on the studied X-ray hand dataset. We further motivate this claim by visualizing the anatomical constraints used in GAFFA as spatial energy heatmaps, which allowed us to find an annotation error in the hand dataset not previously discussed in the literature. Full article

Detecting student behavior in smart classrooms is a critical area of research in educational technology that significantly enhances teaching quality and student engagement. This paper introduces an innovative approach using advanced computer vision and artificial intelligence technologies to monitor and analyze student behavior in real time. Such monitoring assists educators in adjusting their teaching strategies effectively, thereby optimizing classroom instruction. However, the application of this technology faces substantial challenges, including the variability in student sizes, the diversity of behaviors, and occlusions among students in complex classroom settings. Additionally, the uneven distribution of student behaviors presents a significant hurdle. To overcome these challenges, we propose Student Behavior Detection Network (SBD-Net), a lightweight target detection model enhanced by the Focal Modulation module for robust multi-level feature fusion, which augments feature extraction capabilities. Furthermore, the model incorporates the ESLoss function to address the imbalance in behavior sample detection effectively. The innovation continues with the Dyhead detection head, which integrates three-dimensional attention mechanisms, enhancing behavioral representation without escalating computational demands. This balance achieves both a high detection accuracy and manageable computational complexity. Empirical results from our bespoke student behavior dataset, Student Classroom Behavior (SCBehavior), demonstrate that SBD-Net achieves a mean Average Precision (mAP) of 0.824 with a low computational complexity of just 9.8 G. These figures represent a 4.3% improvement in accuracy and a 3.8% increase in recall compared to the baseline model. These advancements underscore the capability of SBD-Net to handle the skewed distribution of student behaviors and to perform high-precision detection in dynamically challenging classroom environments. Full article

As an extremely efficient preprocessing tool, superpixels have become more and more popular in various computer vision tasks. Nevertheless, there are still several drawbacks in the application of hyperspectral image (HSl) processing. Firstly, it is difficult to directly apply superpixels because of the high dimension of HSl information. Secondly, existing superpixel algorithms cannot accurately classify the HSl objects due to multi-scale feature categorization. For the processing of high-dimensional problems, we use the principle of PCA to extract three principal components from numerous bands to form three-channel images. In this paper, a novel superpixel algorithm called Seed Extend by Entropy Density (SEED) is proposed to alleviate the seed point redundancy caused by the diversified content of HSl. It also focuses on breaking the dilemma of manually setting the number of superpixels to overcome the difficulty of classification imprecision caused by multi-scale targets. Next, a space–spectrum constraint model, termed Hyperspectral Image Classification via superpixels and manifold learning (SMALE), is designed, which integrates the proposed SEED to generate a dimensionality reduction framework. By making full use of spatial context information in the process of unsupervised dimension reduction, it could effectively improve the performance of HSl classification. Experimental results show that the proposed SEED could effectively promote the classification accuracy of HSI. Meanwhile, the integrated SMALE model outperforms existing algorithms on public datasets in terms of several quantitative metrics. Full article

The automatic recognition and quantitative analysis of abnormal behavior in mice play a crucial role in behavioral observation experiments in neuroscience, pharmacology, and toxicology. Due to the challenging definition of abnormal behavior and difficulty in collecting training samples, directly applying behavior recognition methods to identify abnormal behavior is often infeasible. This paper proposes ABNet, an AI-empowered abnormal action recognition approach for mice. ABNet utilizes an enhanced Spatio-Temporal Graph Convolutional Network (ST-GCN) as an encoder; ST-GCN combines graph convolution and temporal convolution to efficiently capture and analyze spatio-temporal dynamic features in graph-structured data, making it suitable for complex tasks such as action recognition and traffic prediction. ABNet trains the encoding network with normal behavior samples, then employs unsupervised clustering to identify abnormal behavior in mice. Compared to the original ST-GCN network, the method significantly enhances the capabilities of feature extraction and encoding. We conduct comprehensive experiments on the Kinetics-Skeleton dataset and the mouse behavior dataset to evaluate and validate the performance of ABNet in behavior recognition and abnormal motion detection. In the behavior recognition experiments conducted on the Kinetics-Skeleton dataset, ABNet achieves an accuracy of 32.7% for the top one and 55.2% for the top five. Moreover, in the abnormal behavior analysis experiments conducted on the mouse behavior dataset, ABNet achieves an average accuracy of 83.1%. Full article

Usher syndrome (USH) is an inherited disorder characterized by sensorineural hearing loss (SNHL), retinitis pigmentosa (RP)-related vision loss, and vestibular dysfunction. USH presents itself as three distinct clinical types, 1, 2, and 3, with no biomarker for early detection. This study aimed to explore whether microRNA (miRNA) expression in USH cell lines is dysregulated compared to the miRNA expression pattern in a cell line derived from a healthy human subject. Lymphocytes from USH patients and healthy individuals were isolated and transformed into stable cell lines using Epstein–Barr virus (EBV). DNA from these cell lines was sequenced using a targeted panel to identify gene variants associated with USH types 1, 2, and 3. Microarray analysis was performed on RNA from both USH and control cell lines using NanoString miRNA microarray technology. Dysregulated miRNAs identified by the microarray were validated using droplet digital PCR technology. DNA sequencing revealed that two USH patients had USH type 1 with gene variants in USH1B (MYO7A) and USH1D (CDH23), while the other two patients were classified as USH type 2 (USH2A) and USH type 3 (CLRN-1), respectively. The NanoString miRNA microarray detected 92 differentially expressed miRNAs in USH cell lines compared to controls. Significantly altered miRNAs exhibited at least a twofold increase or decrease with a p value below 0.05. Among these miRNAs, 20 were specific to USH1, 14 to USH2, and 5 to USH3. Three miRNAs that are known as miRNA-183 family which are crucial for inner ear and retina development, have been significantly downregulated as compared to control cells. Subsequently, droplet digital PCR assays confirmed the dysregulation of the 12 most prominent miRNAs in USH cell lines. This study identifies several miRNA signatures in USH cell lines which may have potential utility in Usher syndrome identification. Full article

Developments in drones and imaging hardware technology have opened up countless possibilities for enhancing structural condition assessments and visual inspections. However, processing the inspection images requires considerable work hours, leading to delays in the assessment process. This study presents a semantic segmentation architecture that integrates vision transformers with Laplacian pyramid scaling networks, enabling rapid and accurate pixel-level damage detection. Unlike conventional methods that often lose critical details through resampling or cropping high-resolution images, our approach preserves essential inspection-related information such as microcracks and edges using non-uniform image rescaling networks. This innovation allows for detailed damage identification of high-resolution images while significantly reducing the computational demands. Our main contributions in this study are: (1) proposing two rescaling networks that together allow for processing high-resolution images while significantly reducing the computational demands; and (2) proposing Dmg2Former, a low-resolution segmentation network with a Swin Transformer backbone that leverages the saved computational resources to produce detailed visual inspection masks. We validate our method through a series of experiments on publicly available visual inspection datasets, addressing various tasks such as crack detection and material identification. Finally, we examine the computational efficiency of the adaptive rescalers in terms of multiply–accumulate operations and GPU-memory requirements. Full article

(1) Background: As digital health technology evolves, the role of accurate medical-gloved hand tracking is becoming more important for the assessment and training of practitioners to reduce procedural errors in clinical settings. (2) Method: This study utilized computer vision for hand pose estimation to model skeletal hand movements during in situ aseptic drug compounding procedures. High-definition video cameras recorded hand movements while practitioners wore medical gloves of different colors. Hand poses were manually annotated, and machine learning models were developed and trained using the DeepLabCut interface via an 80/20 training/testing split. (3) Results: The developed model achieved an average root mean square error (RMSE) of 5.89 pixels across the training data set and 10.06 pixels across the test set. When excluding keypoints with a confidence value below 60%, the test set RMSE improved to 7.48 pixels, reflecting high accuracy in hand pose tracking. (4) Conclusions: The developed hand pose estimation model effectively tracks hand movements across both controlled and in situ drug compounding contexts, offering a first-of-its-kind medical glove hand tracking method. This model holds potential for enhancing clinical training and ensuring procedural safety, particularly in tasks requiring high precision such as drug compounding. Full article

Architecture is the stone book of history, and the evolution of architectural styles showcases a non-verbal history constructed through images. As an important part of China’s historical and cultural heritage, the architectural forms and styles of Tibetan Buddhist temples were initially modeled on Tang dynasty temple architecture and gradually evolved into the most significant architectural types in regions such as Tibet and Qinghai in China. Religious architecture has also played a significant role in shaping regional cultural landscapes. Existing research on Tibetan Buddhist temples is primarily focused on qualitative studies of individual temple buildings. This research takes the spatiotemporal evolution of architectural styles of Tibetan Buddhist temples as an entry point and, for the first time, employs ArcGIS technology to visualize the spatial and geographical distribution of Tibetan Buddhist temples from the 7th to the 18th century, establishing a comprehensive academic vision that encompasses both historical stratification and cross-regional spatial correlations. By analyzing the cultural symbolic features embodied in the construction styles of Tibetan Buddhist temples and the visual characteristics reflected in their decorative arts, we propose two spatiotemporal dimensions for the formation and transmission of Tibetan Buddhist temple architectural styles: “Westward Transmission” and “Eastward Diffusion”. Firstly, from the 7th to the 9th centuries, the architectural style and construction techniques of Tang dynasty Buddhist temples were transmitted westward along the Tang–Tibet ancient road, integrating with local Tibetan elements to form the Tubo architectural style, which was further refined into the “Sino–Tibetan Combined Style” with strong visual characteristics around the 13th century. Subsequently, along with the spread of Tibetan Buddhism, this temple architectural style underwent an eastward diffusion from the 13th to the 18th century, reaching regions, such as Sichuan, Qinghai, Gansu, Inner Mongolia, Hebei, and Beijing, presenting a spatial gradient from west to east in the geographical dimension. On this basis, in this research, we construct a historical evolution mapping of Tibetan Buddhist temple architectural styles based on bidirectional transmission, attempting to elucidate that the intrinsic driving forces are religious and the cultural identity that guided the bidirectional transmission mechanism of these architectural styles under the historical context of the formation and dissemination of Tibetan Buddhism from the 7th to the 18th century. Full article

Eye diseases are defined as disorders or diseases that damage the tissue and related parts of the eyes. They appear in various types and can be either minor, meaning that they do not last long, or permanent blindness. Cataracts, glaucoma, and diabetic retinopathy are all eye illnesses that can cause vision loss if not discovered and treated early on. Automated classification of these diseases from fundus images can empower quicker diagnoses and interventions. Our research aims to create a robust model, BayeSVM500, for eye disease classification to enhance medical technology and improve patient outcomes. In this study, we develop models to classify images accurately. We start by preprocessing fundus images using contrast enhancement, normalization, and resizing. We then leverage several state-of-the-art deep convolutional neural network pre-trained models, including VGG16, VGG19, ResNet50, EfficientNet, and DenseNet, to extract deep features. To reduce feature dimensionality, we employ techniques such as principal component analysis, feature agglomeration, correlation analysis, variance thresholding, and feature importance rankings. Using these refined features, we train various traditional machine learning models as well as ensemble methods. Our best model, named BayeSVM500, is a Support Vector Machine classifier trained on EfficientNet features reduced to 500 dimensions via PCA, achieving 93.65 ± 1.05% accuracy. Bayesian hyperparameter optimization further improved performance to 95.33 ± 0.60%. Through comprehensive feature engineering and model optimization, we demonstrate highly accurate eye disease classification from fundus images, comparable to or superior to previous benchmarks. Full article

With the development of agriculture, the complexity and dynamism of orchard environments pose challenges to the perception and positioning of inter-row environments for agricultural vehicles. This paper proposes a method for extracting navigation lines and measuring pedestrian obstacles. The improved YOLOv5 algorithm is used to detect tree trunks between left and right rows in orchards. The experimental results show that the average angle deviation of the extracted navigation lines was less than 5 degrees, verifying its accuracy. Due to the variable posture of pedestrians and ineffective camera depth, a distance measurement algorithm based on a four-zone depth comparison is proposed for pedestrian obstacle distance measurement. Experimental results showed that within a range of 6 m, the average relative error of distance measurement did not exceed 1%, and within a range of 9 m, the maximum relative error was 2.03%. The average distance measurement time was 30 ms, which could accurately and quickly achieve pedestrian distance measurement in orchard environments. On the publicly available TUM RGB-D dynamic dataset, YOLOD-SLAM2 significantly reduced the RMSE index of absolute trajectory error compared to the ORB-SLAM2 algorithm, which was less than 0.05 m/s. In actual orchard environments, YOLOD-SLAM2 had a higher degree of agreement between the estimated trajectory and the true trajectory when the vehicle was traveling in straight and circular directions. The RMSE index of the absolute trajectory error was less than 0.03 m/s, and the average tracking time was 47 ms, indicating that the YOLOD-SLAM2 algorithm proposed in this paper could meet the accuracy and real-time requirements of agricultural vehicle positioning in orchard environments. Full article