Image Dimensions Research Articles

STIDNet: Spatiotemporally Integrated Detection Network for Infrared Dim and Small Targets

Infrared dim and small target detection (IRDSTD) aims to obtain target position information from the background, clutter, and noise. However, for infrared dim and small targets with low signal-to-clutter ratios (SCRs), the detection difficulty lies in the fact that their poor local spatial saliency will lead to missed detections and false alarms. In this work, a spatiotemporally integrated detection network (STIDNet) is proposed for IRDSTD. In the network, a spatial saliency feature generation module (SSFGM) employs a U-shaped network to extract deep features from the spatial dimension of the input image in a frame-by-frame manner and splices them based on the temporal dimension to obtain an airtime feature tensor. IRDSTs with direction-of-motion consistency and strong interframe correlation are reinforced, and randomly generated spurious waves, noise, and other false alarms are inhibited via a fixed-weight multiscale motion feature-based 3D convolution kernel (FWMFCK-3D). A mapping from the features to the target probability likelihood map is constructed in a spatiotemporal feature fusion module (STFFM) by performing 3D convolutional fusion on the spatially localized saliency and time-domain motion features. Finally, several ablation and comparison experiments indicate the excellent performance of the proposed network. For infrared dim and small targets with SCRs < 3, the average AUC value still reached 0.99786.

Exploring the Voice of Inbound Tourists: A Study on the Perceived Image of Ethnic-Minority Village Tourism with Impact on Satisfaction

ABSTRACT The opinions and emotions expressed by tourists were the genuine perception of the destination image. To listen to the voice of inbound tourists, this research introduces a new analytical framework through two studies to explore the perceived destination image of ethnic-minority village tourism. Study 1 employed content and sentiment analyses to reveal the cognitive and affective images. Study 2 quantitatively assesses image dimensions’ impact on satisfaction using online reviews through regression analysis. Findings underscore that (1) the perceived destination image includes four dimensions: natural landscape, cultural attraction, tourism environment and touristic service, as well as infrastructure and facility. Eight themes were identified, namely old, local, park, minority, crowd, season, rice, platform. And the affective image tends to be positive; (2) there is a significant positive correlation between the overall perceived destination image and the satisfaction level of inbound tourists visiting ethnic-minority villages, and tourism environment and touristic service exerts the most pronounced impact on satisfaction. This research innovatively transformed textual data into numerical data. It enriches the literature on inbound tourism in China’s ethnic regions, providing practical insights for improving the international competitiveness of ethnic-minority villages in the post-COVID-19 era.

‘The Good Place’: investigating the social responsibility image of countries and its impact on the attractiveness of highly skilled workers

AbstractThis article aims to bridge the gap between corporate social responsibility and place branding literature by (1) examining the nature and dimensions of the social responsibility image of countries (SRIC), (2) developing a scale for SRIC and (3) measuring its impact on nation brand identification and intention to apply for a job. Leveraging social identity theory, associative network theory and selection–attraction–attrition theory, the study employs a mixed method approach comprising semi-structured interviews, focus groups and a survey with UK and Italian highly skilled workers. Findings reveal the complexity of this multidimensional concept which integrates economic, ethical and environmental factors. SRIC exerts a significant impact on both nation brand identification and intention to apply for a job vacancy. Based on the results, organisations and governments interested in luring the best candidates should work in partnership to develop adequate programmes and a consistent narrative that highlight economic, ethical and environmental responsibilities of the place.

THE IMPACT OF AGROTOURISM DESTINATION IMAGE ON TOURIST’S LOYALTY IN ZAGHOUAN, TUNISIA: MODERATING ROLE OF VISIT’S EXPERIENCE

This study tests the influence of destination image on loyalty. It also examines the moderation effect of visitors’ experiences in the link between the two main components of destination image and loyalty. For this reason, responses from 302 visitors at Zaghouan, Tunisia were collected using a pre-examined questionnaire form. The collected responses were analyzed with SmartPLS SEM and Multi-group analysis. The findings showed that destination image significantly and positively affected visitors’ intention to revisit and recommend agrotourism destination to others. The results confirmed that destination image dimensions (cognitive and affective) influence visitors’ loyalty. These influences are significantly moderated by tourist’s experiences. New visitors with new experiences have less influence on the link between image and loyalty than regular visitors. The findings have some propositions for tourism destination marketers and scholars.

Adaptive Compression and Reconstruction for Multidimensional Medical Image Data: A Hybrid Algorithm for Enhanced Image Quality.

Spatial regions within images typically hold greater priority over adjacent areas, especially in the context of medical images (MI) where minute details can have significant clinical implications. This research addresses the challenge of compressing medical image dimensions without compromising critical information by proposing an adaptive compression algorithm. The algorithm integrates a modified image enhancement module, clustering-based segmentation, and a variety of lossless and lossy compression techniques. Edge enhancement contrast limited adaptive histogram equalization (EE-CLAHE) and 2D adaptive anisotropic diffusion filter are employed to enhance and denoise the images, followed by adaptive expectation maximization clustering (AEMC) for segmentation into regions of interest (ROI) and non-ROI. The clustering process is optimized utilizing fuzzy c-means (FCM) and Otsu thresholding. Subsequently, distinct compression schemes are applied to ROI and non-ROI regions, such as Coiflet + Haar, Coiflet + Daubecheis, modified SPIHT Huffman, EZW, and SPIHT algorithms, to ensure effective storage and transmission while preserving diagnostic details. Experimental results demonstrate that the combination of the modified SPIHT Huffman algorithm for ROI and EZW for non-ROI yields superior reconstruction quality across various measures, enabling comprehensive analysis of multi-dimensional images from MRI, CT, and X-ray modalities.

Recent Technologies on 2D and 3D Imaging Flow Cytometry.

Imaging flow cytometry is a technology that performs microscopy image analysis of cells within flow cytometry and allows high-throughput, high-content cell analysis based on their intracellular molecular distribution and/or cellular morphology. While the technology has been available for a couple of decades, it has recently gained significant attention as technical limitations for higher throughput, sorting capability, and additional imaging dimensions have been overcome with various approaches. These evolutions have enabled imaging flow cytometry to offer a variety of solutions for life science and medicine that are not possible with conventional flow cytometry or microscopy-based screening. It is anticipated that the extent of applications will expand in the upcoming years as the technology becomes more accessible through dissemination. In this review, we will cover the technical advances that have led to this new generation of imaging flow cytometry, focusing on the advantages and limitations of each technique.

Service Recovery Strategy in Private Hospitals: The Role of Experience, Symbolic, and Functional Brand Images

This study investigates the influence of brand image on service recovery strategy, customer satisfaction, word-of-mouth communication, and revisit intentions within the context of private hospitals. The research identifies four dimensions of brand image: experiential, symbolic, functional, and social. The findings reveal that experiential, symbolic, and functional images positively impact service recovery strategy, while the social image does not have a significant positive effect. Service recovery strategies based on perceived justice significantly enhance customer satisfaction, which, in turn, fosters positive word-of-mouth and increases revisit intentions. The study highlights the importance of managing brand image to improve service recovery outcomes and maintain positive behavioral intention. Theoretical implications suggest further exploration of brand image factors and perceived justice in service recovery. Managerial implications emphasise the need for targeted marketing strategies that enhance functional and experiential brand images while avoiding social status associations. This study offers valuable insights for academia and practice, contributing to understanding and managing brand image and service recovery strategies in private hospitals.

DentaGAN: GAN-Based Synthetic Individual Dental Data Generation in Radiographic Images

Panoramic radiographs are a low radiation exposure type often used as a data source for many deep learning algorithms. On the other hand, the operational structure of a traditional deep learning algorithm requires a large amount of data, which is a major problem for many researchers. It is aimed to overcome this problem through deep GAN models, many versions of which have been developed recently. The main purpose of the study is to generate a two-stage GAN model for data with the same image dimensions. The study is carried out in the form of inputting panoramic images containing a whole view, as well as single tooth data whose performance is desired to be measured, to the architecture. The generator model created for each tooth object in all panoramic radiographs generates new tooth objects that the model has yet to encounter in the dataset. Fréchet Inception Distance was used as a performance metric by measuring the distance for the Inception-v3 activation distributions for the real samples in the generated and training set. Thus, the statistical similarity of these two groups obtained from the experimental results was observed in the part of the experimental results. The cropped individual tooth classes were much more successful than the entire panoramic dataset.

Comparative Analysis of YOLOv5/v8/v9 for Object Detection, Tracking, and Human Action Recognition in Combat Sports

YOLO models are widely used object detectors in computer vision (CV). This study investigates the relative performance of YOLOv5, YOLOv8, and YOLOv9 for object detection, tracking, and human action recognition in combat sports. The models were evaluated using curated datasets encompassing various combat scenarios, athlete movements, and equipment configurations. Pre-processing protocols and augmentation techniques were applied to improve model accuracy and generalizability, including automated orientation correction, image dimension standardisation, contrast enhancement, and methods such as zoom, rotation, shear, and grayscale conversion. The key findings provide insight into the comparative performance of the models across various evaluation metrics, such as precision, recall, and mean average precision. Each model's ability to detect, track, and recognise human actions in dynamic combat sports environments is evaluated. Computational efficiency and real-time performance were assessed as these are important indicators for practical applications in coaching, training, and competitive scoring systems. The findings suggest that YOLOv8 offers the best balance of precision and recall, making it particularly suitable for real-time applications in combat sports analytics. This study contributes to advancing CV technologies in combat sports analytics, with potential implications for improving athletic training methods, facilitating personalised coaching interventions, and enhancing objectivity and consistency in competitive scoring processes in combat sports.

An Evaluation of Image Slicing and YOLO Architectures for Object Detection in UAV Images

Object detection in aerial images poses significant challenges due to the high dimensions of the images, requiring efficient handling and resizing to fit object detection models. The image-slicing approach for object detection in aerial images can increase detection accuracy by eliminating pixel loss in high-resolution image data. However, determining the proper dimensions to slice is essential for the integrity of the objects and their learning by the model. This study presents an evaluation of the image-slicing approach for alternative sizes of images to optimize efficiency. For this purpose, a dataset of high-resolution images collected with Unmanned Aerial Vehicles (UAV) has been used. The experiments evaluated using alternative YOLO architectures like YOLOv7, YOLOv8, and YOLOv9 show that the image dimensions significantly change the performance results. According to the experiments, the best mAP@05 accuracy was obtained by slicing 1280×1280 for YOLOv7 producing 88.2. Results show that edge-related objects are better preserved as the overlap and slicing sizes increase, resulting in improved model performance.

Industry Image Perceptions and Organizational Attractiveness: Results of an International Survey

ABSTRACTExtending the research on corporate brand image and recruitment, this study investigates the influence of industry image on organizational attractiveness in a cross–national context. Drawing from signaling theory and the application of the instrumental‐symbolic image framework, we apply an experimental vignette design in the renewable energy industry (REI) and the oil and gas exploration and production industry (OGI) with potential job applicants in France, Germany, and the United Kingdom. We conceptualize national context as collective signaling environments. Results from 550 respondents indicate that the REI and OGI differ in most of the instrumental and symbolic image dimensions. The instrumental image dimension of pay and the three symbolic image dimensions of sincerity, innovativeness, and prestige predict organizational attractiveness. Moreover, sincerity, innovativeness, and prestige carry a mediating effect in the link between industry affiliation and organizational attractiveness. Findings also demonstrate that image perceptions of the REI and OGI vary across countries such that the already more favorable image perceptions regarding the REI are for the most part even more pronounced in France. Implications for theory and tailored recommendations for practice are provided.

Magnetic resonance imaging (MRI) and clinical features of different parts of the pancreas involved in acute pancreatitis: a cross-sectional study.

Patients with acute pancreatitis (AP) have different sites of pancreatic involvement. The aim of this study was to investigate the differences in magnetic resonance imaging (MRI) findings and clinical features of different sites of involvement (subtypes) in AP, with a view to complement and complete the classification of AP based on anatomical imaging features. We consecutively collected data from inpatients with AP from January 2018 to October 2022 at a tertiary care hospital. The patients with AP were classified into three subtypes by MRI: type I mainly involved the head of the pancreas; type II mainly involved the body and tail of the pancreas; and type III involved the entire pancreas (head, body, and tail simultaneously). We examined the MRI findings and clinical features of the three subtypes, including their prevalence, gender, etiology, age, assessment of severity, prevalence of hypertension, diabetes mellitus, coronary artery disease, laboratory markers, prognosis, necrosis, and the incidence of complications. The three subgroups were analyzed using one-way analysis of variance (ANOVA), Kruskal-Wallis H-test, Chi-squared test or Fisher's exact probability method depending on the data distribution, and logistic regression and linear regression were used to determine the risk factors for poor short-term prognosis of AP and the number of days in hospital. Results were considered statistically significant at P<0.05. Among the 240 patients recruited, the mean age was 51±15 years (range, 12-89 years); 146 (60.83%) were male and 94 (39.17%) were female. Biliary pancreatitis accounted for 45.00% (108/240), hyperlipidemic pancreatitis for 33.75% (81/240), alcoholic pancreatitis for 8.75% (21/240), and unknown etiology for 12.5% (30/240). Some 81.25% (195/240) of the cases were edematous pancreatitis, whereas 18.75% (45/240) were necrotizing pancreatitis. Overall, 75 patients (31.25%) had type I AP, 108 patients (45.00%) had type II AP, and 57 patients (23.75%) had type III AP. These three subtypes were significantly different in terms of etiology, incidence of diabetes, C-reactive protein (CRP), severity, incidence of necrosis, local complications, clinical and imaging severity scores, and prognosis (P<0.05). Total pancreatic involvement (Type III) was the most severe subtype, with hyperlipidemia as the main cause. Regression analysis revealed that subtype classification is an important risk factor for prognosis. We classified AP into three subtypes based on different sites of involvement and revealed the MRI features and clinical characteristics of each subtype of AP. The subtype classification helps to characterize AP from the imaging dimension and predict the prognosis. The results of this study could be a target for future studies to adopt new classification methods.

Enabling FEM-based absolute permeability estimation in giga-voxel porous media with a single GPU

The characterization of porous media via digital testing usually relies on intensive numerical computations that can be parallelized in GPUs. For absolute permeability estimation, Stokes flow simulations are carried out at the micro-structure to recover velocity fields that are used in upscaling with Darcy’s law. Digital models of samples can be obtained via micro-computed tomography (μCT) scans. As μCT data is three-dimensional, meshes grow cubically with image dimensions, causing the numerical problem at hand to become compute- and memory-bound as either resolution improves or larger fields-of-view are considered. While the usual focus is on accelerating solvers, memory usage continues to be a significant limitation for analyses of representative volumes in relatively accessible hardware. In this work, we explore the possibility of implementing MINRES solvers in GPU that favor a reduction in memory allocation. These solvers are applied to matrix-free FEM-based permeability characterization of μCT images. Our goal is to enable the study of 10003 voxel images in single GPU machines. Implementations that only require five, three, or two n-sized vectors of variables are presented, with n being the number of unknowns. Further, we employ a mesh numbering strategy that enables node-by-node massively parallel operations within a non-monolithic voxel-based pore space without storing connectivity tables. The proposed solvers, available through the open-source chfem software, are verified against analytical models for simple three-dimensional micro-structures, then are validated against numerical Digital Petrophysics benchmarks. A consumer-grade graphics card with 12GB of RAM is employed for the characterization of images with up to roughly 540 million voxels in a matter of tens of minutes. Stokes flow FEM-based simulations in meshes with 449 million degrees-of-freedom (DOFs) are carried out in 9 to 15 min, allocating less than 10GB in global memory. Finally, simulations on three 10003 carbon fiber domains, amounting to more than 3.7 billion DOFs, were run on a high-end GPU with 80GB of RAM in under 2.5 h, achieving very close agreement with flow-tube permeability experiments.

IoMT-Based Smart Intelligent Healthcare System Using Optimization-Driven Deep Residual Network for Brain Tumor Detection

Medical information system, like the Internet of Medical Things (IoMT), has gained more attention in recent decades. Disease diagnosis is an important facility of the medical healthcare system. Wearable devices become popular in a wide range of applications in the health monitoring system and this has stimulated the increasing growth of IoMT. Recently, a smart healthcare system has been more effective, and various methods have been developed to classify the disease at the beginning stage. To capture the patient’s information and detect the disease, a new framework is designed using the developed Conditional Auto regressive Mayfly Algorithm (CAMA)-based Deep Residual Network (DRN). Initially, pre-processing is done by the T2FCS filtering technique to increase the image quality by eliminating noises. The second step is segmentation. Here, the segmentation of brain tumor is done using U-Net. After that, data augmentation is performed to enhance image dimensions using the techniques, such as flipping, shearing, and translation to solve the issues of data samples. After processing the data augmentation mechanism, the next step is brain tumor detection, which is done using DRN. Here, DRN is trained by the proposed CAMA, which is the integration of conditional auto regressive value at risk (CAViaR) with the mayfly algorithm (MA). The developed model reduces computational complexity and increases effectiveness and robustness. The proposed CAMA-based DRN outperformed with an utmost testing accuracy of 0.921, sensitivity of 0.931, specificity of 0.928, distance of 52.842 and trust of 0.697.

Psychological Mediators of the Association between Obesity and Symptoms of Depression, Anxiety, and Stress

Plain Language SummaryThere is still paucity of knowledge about which factors can mediate the link between obesity and mental health problems. This study aimed to investigate factors that can explain an indirect link between unhealthy weight profiles (having overweight or obesity) and symptoms of depression, anxiety, and stress. A sample of 407 adults (≥18 years old) with different weight profiles recruited from general population was assessed for symptoms of depression, anxiety, and stress, as well as for other psychological dimensions related to body image and to the way people self-regulate emotions. Body investment difficulties in relation to body image and body care, and emotion regulation difficulties related to a tendency towards negative secondary responses to negative emotions, and/or denial of distress, significantly mediated the association between obesity and symptoms of depression. The association between obesity and symptoms of anxiety and stress was significantly mediated by body investment difficulties related to body image concerns. The current study brings evidence on specific dimensions of emotion regulation and body image that play a key role for the co-occurrence of mental health problems in individuals with obesity.

Brand Hate as a Mediator: The Study of Brand Image and Brand Relationship Quality in Virtual Brand Communities

The goal of this study is to look at the relationship between the independent variable brand image, mediated by brand hate, and the dependent variable of brand relationship quality (BRQ) in a virtual brand community. This study adopts a quantitative design using the random stratified sampling method to select 340 Xiaomi cell phone users in China to fill out a questionnaire to collect empirical collection and analyze the interrelationships between the constructs based on PLS-SEM. The results show that of the three dimensions of brand image (functional, symbolic and experiential) in relation to BRQ, only symbolic image has a non-significant relationship with BRQ. Brand hate played a significant mediating role in the relationship between brand image and BRQ. The theoretical and practical contributions are explained for insight enhancement toward the variables involved and further support existing literature. Brand image composition and brand hate composition are closely related to BRQ. In particular, this study aims to determine the factors that affect BRQ in the virtual brand community (VBC) according to the VBC characteristics. Therefore, it is necessary to strengthen the maintenance of brand image, reduce brand hate, and improve the BRQ in the cell phone VBC.

How destination image projected on social media influences online sales of tourism services: exploring the moderating role of tourists’ experience

ABSTRACT While previous research has focused on the cognitive and affective dimensions of destination image and their effects on tourists’ attitudes and intentions (rather than actual behaviours), this study takes a three-dimensional approach to examine tourists’ objective responses. It examines how cognitive, affective, and sensory destination images projected by the destination marketing organisation (DMO) through social media influence its online sales of tourism services. Analysing 1676 social media posts from a DMO, findings reveal that cognitive and sensory images positively affect online sales. Additionally, tourists’ previous experience with the destination moderates the effects of the three dimensions of projected destination image.

ON-BOARD LOG AND COORDINATE TRANSFORMATION FOR DETECTED OBJECTS ON THE SURFACE OF WATER

Context. The relevance of the work is to the demand for UAV technologies with the integration of artificial intelligence in today’s conditions. Objective. The goal of the work is to develop a minimum working version of the UAV explorer and software for controlling the UAV data. Method. The proposed mathematical description, which calculates the coordinates of the object, based on the dimensions of the original image from the camera, the dimensions of the image with which the neural network works, the angle of the field of view of the camera, the position of the UAV and the angles of roll, pitch and yaw, allows you to transfer the coordinates of the object, of the found NN, in the image to the geographical coordinates, thereby moving away from the rigid reference to the coordinates of the UAV. Results. The problem of systematization of objects detected during the mission on the surface of water bodies was solved bycreating a flight log, organizing interaction with a neural network, applying post-processing of recognized objects, mathematically transforming the coordinates of objects for display and visualization into geographic coordinates, thereby move away from the rigid reference to the coordinates of the UAV. Conclusions. A workable logbook generation and storage system has been created, which takes into account the peculiarities of information presentation in the logbook, and ensures effective interaction of the components of the created information system within the proposed hardware and software complex, which allows organizing the process of researching water bodies using the SITL environment from the flight controller developers.

Relationships among eye dimensions in magnetic resonance images by sex, age, and strabismus type in Japanese patients with acquired strabismus and high myopia

PurposeTo investigate the relationships among eye dimensions in magnetic resonance imaging (MRI) scans by sex, age, and strabismus type in Japanese patients with acquired strabismus and high myopia.Study designRetrospective clinical case series.MethodsWe included 58 eyes of 29 patients with acquired strabismus and high myopia (mean age ± standard deviation: 60.2 ± 14.7 years, axial length [AL]: 28.69 ± 2.12 mm). For all eyes, the equatorial diameter of the globe/AL ratio (EAR) and the globe/orbit volume ratio (GOR) were measured using MRI. EAR and GOR values were compared between the following groups: 9 men vs. 20 women; 8 younger (< 56 years) vs. 21 older (≥ 56 years) patients; and non-esotropia strabismus (NES: 7 patients) vs. esotropia (ET: 13 patients) vs. restrictive strabismus (RS: 9 patients) groups.ResultsFemale patients had a smaller EAR (0.87 ± 0.07) and larger GOR (0.38 ± 0.04) than male patients (0.92 ± 0.05 and 0.35 ± 0.03, both P < 0.01). Older patients had a smaller EAR (0.87 ± 0.07) than younger ones (0.93 ± 0.04, P < 0.01), without significant differences in GOR. EAR (NES: 0.92 ± 0.06, ET: 0.86 ± 0.06, RS: 0.89 ± 0.09) significantly differed among the three strabismus groups (P = 0.02: post-hoc test: NES vs. ET, P = 0.02; NES vs. RS, P = 0.49; RS vs. ET, P = 0.67), but no significant differences in GOR were found (P = 0.12).ConclusionsAmong patients with acquired strabismus and high myopia, women, older patients, and those with esotropia exhibit a smaller EAR and longer sphere shape with AL as the major axis. The parameter EAR might be useful for evaluating the pathogenesis of strabismus associated with high myopia.

FCSwinU: Fourier Convolutions and Swin Transformer UNet for Hyperspectral and Multispectral Image Fusion.

The fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) provides a cost-effective approach to obtaining high-resolution hyperspectral images (HR-HSI). Existing methods primarily based on convolutional neural networks (CNNs) struggle to capture global features and do not adequately address the significant scale and spectral resolution differences between LR-HSI and HR-MSI. To tackle these challenges, our novel FCSwinU network leverages the spectral fast Fourier convolution (SFFC) module for spectral feature extraction and utilizes the Swin Transformer's self-attention mechanism for multi-scale global feature fusion. FCSwinU employs a UNet-like encoder-decoder framework to effectively merge spatiospectral features. The encoder integrates the Swin Transformer feature abstraction module (SwinTFAM) to encode pixel correlations and perform multi-scale transformations, facilitating the adaptive fusion of hyperspectral and multispectral data. The decoder then employs the Swin Transformer feature reconstruction module (SwinTFRM) to reconstruct the fused features, restoring the original image dimensions and ensuring the precise recovery of spatial and spectral details. Experimental results from three benchmark datasets and a real-world dataset robustly validate the superior performance of our method in both visual representation and quantitative assessment compared to existing fusion methods.