Search results

Data quality and data resolution are essential for computer vision tasks like medical image processing, object detection, pattern recognition and so on. Super-resolution is a way to increase the image resolution, and super-resolved images contain more information compared to their low-resolution counterparts. The purpose of this study is analyzing the effects of the super resolution models trained before on object detection for aerial images.

Two different models were trained using the Super-Resolution Generative Adversarial Network (SRGAN) architecture on two aerial image data sets, the xView and the Dataset for Object deTection in Aerial images (DOTA). This study uses these models to increase the resolution of aerial images for improving object detection performance. This study analyzes the effects of the model with the best perceptual index (PI) and the model with the best RMSE on object detection in detail.

Super-resolution increases the object detection quality as expected. But, the super-resolution model with better perceptual quality achieves lower mean average precision results compared to the model with better RMSE. It means that the model with a better PI is more meaningful to human perception but less meaningful to computer vision.

The contributions of the authors to the literature are threefold. First, they do a wide analysis of SRGAN results for aerial image super-resolution on the task of object detection. Second, they compare super-resolution models with best PI and best RMSE to showcase the differences on object detection performance as a downstream task first time in the literature. Finally, they use a transfer learning approach for super-resolution to improve the performance of object detection.

High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.

There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.

In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.

The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

Today's marketing is dominated by decision-making based on artificial intelligence and machine learning. This study focuses on one semi- and unsupervised machine learning technique, generative adversarial networks (GANs). GANs are a type of deep learning architecture capable of generating new data similar to the training data that were used to train it, and thus, it is designed to learn a generative model that can produce new samples. GANs have been used in multiple marketing areas, especially in creating images and video and providing customized consumer contents. Through providing a holistic picture of GANs, including its advantage, disadvantage, ethical considerations, and its current application, the study attempts to provide business some strategical orientations, including formulating strong marketing positioning, creating consumer lifetime values, and delivering desired marketing tactics in product, promotion, pricing, and distribution channel. Through using GANs, marketers will create unique experiences for consumers, build strategic focus, and gain competitive advantages. This study is an original endeavor in discussing GANs in marketing, offering fresh insights in this research topic.

Light field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.

This work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).

In three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.

(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.

The susceptible-infectious-susceptible (SIS) infectious disease models without spatial heterogeneity have limited applications, and the numerical simulation without considering models’ global existence and uniqueness of classical solutions might converge to an impractical solution. This paper aims to develop a robust and reliable numerical approach to the SIS epidemic model with spatial heterogeneity, which characterizes the horizontal and vertical transmission of the disease.

This study used stability analysis methods from nonlinear dynamics to evaluate the stability of SIS epidemic models. Additionally, the authors applied numerical solution methods from diffusion equations and heat conduction equations in fluid mechanics to infectious disease transmission models with spatial heterogeneity, which can guarantee a robustly stable and highly reliable numerical process. The findings revealed that this interdisciplinary approach not only provides a more comprehensive understanding of the propagation patterns of infectious diseases across various spatial environments but also offers new application directions in the fields of fluid mechanics and heat flow. The results of this study are highly significant for developing effective control strategies against infectious diseases while offering new ideas and methods for related fields of research.

Through theoretical analysis and numerical simulation, the distribution of infected persons in heterogeneous environments is closely related to the location parameters. The finding is suitable for clinical use.

The theoretical analysis of the stability theorem and the threshold dynamics guarantee robust stability and fast convergence of the numerical solution. It opens up a new window for a robust and reliable numerical study.

This study tries to examine how supply chain (SC) absorptive capacity (AC), SC ambidexterity, SC risk mitigation and supply chain agility (SCA) affect SC efficacy (SCE) in manufacturing firms (MFs) in the Middle East region.

Using a quantitative approach through a survey-based study, 1,004 questionnaires were distributed to the MFs that are listed in the chambers of the industries of Jordan, Egypt, Saudi Arabia and Bahrain in the Middle East region, with 239 useable and valid responses retrieved for analysis, representing a 23.8% response rate. The main respondents were chief executive managers, operations managers, managers and logistics managers from both mid and top levels. The conceptual model was tested by using a hypothesis-testing deductive approach. The findings are based on covariance-based analysis and structural equation modeling (SEM) using partial least squares-SEM (PLS-SEM) software.

This study illustrates a significant relationship between SC AC, SC ambidexterity, SC risk mitigation and SCA on SCE. Further, the findings indicate that there is a significant effect of SC risk mitigation as a mediating factor in the relationship between SC AC, and SC ambidexterity on SCE directly and indirectly, as well through a moderating effect of SCA in these relations. Finally, there is a significant direct and indirect effect of SCA in the relationship between SC AC and SC ambidexterity on SCE as a moderating factor.

This study presents theoretical and empirical insights that both SC risk mitigation and SCA are proper logistics features for mediating and moderating extends the literature by adding a positive role of SC AC and SC ambidextrousness in mitigating SC risks. However, this study adds up the SC literature by evidencing moderating role of SCA between the absorptive capacities, ambidexterity on SCE. Such findings of this study can provide insightful implications for managers and practitioners at different levels in and efficacy among MFs (MFs, stakeholders and policymakers regarding the importance of using the three mentioned enablers on SCE) in MFs, particularly in the Middle Eastern firms and in developing countries in general East region.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

This paper aims to estimate contact location from sparse and high-dimensional soft tactile array sensor data using the tactile image. The authors used three feature extraction methods: handcrafted features, convolutional features and autoencoder features. Subsequently, these features were mapped to contact locations through a contact location regression network. Finally, the network performance was evaluated using spherical fittings of three different radii to further determine the optimal feature extraction method.

This paper aims to estimate contact location from sparse and high-dimensional soft tactile array sensor data using the tactile image.

This research indicates that data collected by probes can be used for contact localization. Introducing a batch normalization layer after the feature extraction stage significantly enhances the model’s generalization performance. Through qualitative and quantitative analyses, the authors conclude that convolutional methods can more accurately estimate contact locations.

The paper provides both qualitative and quantitative analyses of the performance of three contact localization methods across different datasets. To address the challenge of obtaining accurate contact locations in quantitative analysis, an indirect measurement metric is proposed.

The study aims to assess the efficiency of nanocomposite to improve the properties of gap-filling materials for pottery artifacts.

Five different pastes were used in the laboratory studies. The pastes consist mainly of pottery powder (grog), dental plaster, microballoons and an adhesive of Primal AC33, nano-silica and nano kaolinite in various concentrations. The prepared samples were subjected to accelerated heat and light aging. Besides, some investigations were used to evaluate the efficacy of the additive nanomaterials, such as TEM, digital and scanning electron microscopy microscopes. Contact angle, color change, shrinkage degree, physical properties and compressive strength tests were also conducted.

The results indicated that using Nano-silica considerably improves the mechanical strength and decreases the shrinkage of gap-filling materials. According to the results, a mixture of grog, microballoons and Primal AC33/Nano-silica Nanocomposites is the optimal gap-filling paste for archaeological pottery. Moreover, this paste showed a higher contact angle (120°), lower color change (ΔE = 2.62), lower shrinkage (3.3%), lower water absorption (3.36%), lower porosity (5.05%) and higher compressive strength (5124 N/mm²).

This paper attains to develop an economic polymer-nanocomposite that can be used with gap-filling materials for pottery artifacts.

The purpose of this study is to evaluate the effectiveness of nanocontainer solutions in removing deteriorated and aged polymers commonly used in coating and consolidating archaeological glass.

This study focused on characterizing glass surfaces coated with two commonly used polymeric materials in archaeological glass preservation. Furthermore, the study evaluates the elimination of these coatings from the surfaces by using innovative aqueous systems composed of micellar solutions (MS) and oil-in-water (O/W) Texapon-P microemulsions (TEX). Glass samples coated with selected polymers were subjected to thermal and photochemical aging to simulate natural degradation conditions. This study aimed to evaluate the effectiveness of nanocontainer aqueous systems compared to acetone (Ac), a conventional solvent commonly used for removal procedures. The characterization procedures involved transmission electron microscopy, USB digital microscopy, scanning electron microscopy, color alteration and gravimetric measurement.

The findings indicate that the effectiveness of novel techniques using aqueous nanocontainer systems is quite promising when considering a “green approach” to preserving cultural heritage. Microscopic examination demonstrated the efficacy of MS in effectively removing acrylic and vinyl polymers from the glass surface. Furthermore, TEX proved effective in removing polyvinyl acetate (PVA) over Paraloid B72 (B-72). In addition, the measurement of color alteration values revealed a decrease after using MS compared to the standard sample before applying the polymers, with values of ΔE = 1.48 and 1.82 for B-72 polymer and PVA, respectively.

This research provides nanocontainer solutions for removing aged polymers from the glass surface. This makes the current study a promising step for treating archaeological glass.