Search Results (21,813)

Hyperspectral video acquisition requires a precise balance between spectral and temporal resolution, often achieved through compressive sampling using two-dimensional detectors and spectral reconstruction algorithms. However, the reliance on spatial light modulators for coding reduces optical efficiency, while complex recovery algorithms hinder real-time reconstruction. To address these challenges, we propose a digital-micromirror-device-based complementary dual-channel hyperspectral (DMD-CDH) video imaging system. This system employs a DMD for simultaneous light splitting and spatial encoding, enabling one channel to perform non-aliasing spectral sampling at lower frame rates while the other provides complementary high-rate sampling for panchromatic video. Featuring high optical throughput and efficient complementary sampling, the system ensures reliable hyperspectral video reconstruction and serves as a robust ground-based validation platform for remote sensing applications. Additionally, we introduce tailored optical error calibration and fixation techniques alongside a lightweight hyperspectral fusion network for reconstruction, achieving hyperspectral frame rates exceeding 30 fps. Compared to the existing models, this system simplifies the calibration process and provides a practical high-performance solution for real-time hyperspectral video imaging. Full article

To address the vulnerability of rolling bearings to noise interference in industrial settings, along with the problems of weak noise resilience and inadequate generalization in conventional residual network frameworks, this study introduces an adaptive denoising residual network (AD-ResNet) for diagnosing rolling bearing faults. Initially, the sensors collect the bearing vibration signals, which are then converted into two-dimensional grayscale images through the application of a continuous wavelet transform. Then, a spatial adaptive denoising network (SADNet) architecture is incorporated to comprehensively extract multi-scale information from noisy images. By exploiting the improved pyramid squeeze attention (IPSA) module, which excels in extracting representative features from channel attention vectors, this unit substitutes the standard convolutional layers present in typical residual networks. Ultimately, this model was validated through experiments using publicly available bearing datasets from CWRU and HUST. The findings suggest that with −6 dB Gaussian white noise, the average accuracy of recognition achieves a rate of 90.96%. In scenarios of fluctuating speeds accompanied by strong noise, the recognition accuracy can reach 89.54%, while the training time per cycle averages merely 3.65 s. When compared to other widely utilized fault diagnosis techniques, the approach described in this paper exhibits enhanced noise resistance and better generalization capabilities. Full article

This paper addresses the challenges of limited training data and suboptimal environmental conditions in image processing tasks, such as underwater imaging with poor lighting and distortion. Neural networks, including Convolutional Neural Networks (CNNs) and Transformers, have advanced image analysis but remain constrained by computational demands and insufficient data. To overcome these limitations, we propose a novel split-and-concatenate method for self-attention mechanisms. By splitting Query and Key matrices into submatrices, performing cross-multiplications, and applying weighted summation, the method optimizes intermediate variables without increasing computational costs. Experiments on a real-world crack dataset demonstrate its effectiveness in improving network performance. Full article

Background: The rapid global spread of the monkeypox virus has led to serious issues for public health professionals. According to related studies, monkeypox and other types of skin conditions can spread through direct contact with infected animals, humans, or contaminated items. This disease can cause fever, headaches, muscle aches, and enlarged lymph nodes, followed by a rash that develops into lesions. To facilitate the early detection of monkeypox, researchers have proposed several AI-based techniques for accurately classifying and identifying the condition. However, there is still room for improvement to accurately detect and classify monkeypox cases. Furthermore, the currently proposed pre-trained deep learning models can consume extensive resources to achieve accurate detection and classification of monkeypox. Hence, these models often need significant computational power and memory. Methods: This paper proposes a novel lightweight framework called DeepGenMonto accurately classify various types of skin diseases, such as chickenpox, melasma, monkeypox, and others. This suggested framework leverages an attention-based convolutional neural network (CNN) and a genetic algorithm (GA) to enhance detection accuracy while optimizing the hyperparameters of the proposed model. It first applies the attention mechanism to highlight and assign weights to specific regions of an image that are relevant to the model’s decision-making process. Next, the CNN is employed to process the visual input and extract hierarchical features for classifying the input data into multiple classes. Finally, the CNN’s hyperparameters are adjusted using a genetic algorithm to enhance the model’s robustness and classification accuracy. Compared to the state-of-the-art (SOTA) models, DeepGenMon features a lightweight design that requires significantly lower computational resources and is easier to train with few parameters. Its effective integration of a CNN and an attention mechanism with a GA further enhances its performance, making it particularly well suited for low-resource environments. DeepGenMon is evaluated on two public datasets. The first dataset comprises 847 images of diverse skin diseases, while the second dataset contains 659 images classified into several categories. Results: The proposed model demonstrates superior performance compared to SOTA models across key evaluation metrics. On dataset 1, it achieves a precision of 0.985, recall of 0.984, F-score of 0.985, and accuracy of 0.985. Similarly, on dataset 2, the model attains a precision of 0.981, recall of 0.982, F-score of 0.982, and accuracy of 0.982. Moreover, the findings demonstrate the model’s ability to achieve an inference time of 2.9764 s on dataset 1 and 2.1753 s on dataset 2. Conclusions: These results also show DeepGenMon’s effectiveness in accurately classifying different skin conditions, highlighting its potential as a reliable and low-resource tool in clinical settings. Full article

Artificial intelligence, with its remarkable adaptability, has gradually integrated into daily life. The emergence of the self-attention mechanism has propelled the Transformer architecture into diverse fields, including a role as an efficient and precise diagnostic and predictive tool in medicine. To enhance accuracy, we propose the Double-Attention (DA) method, which improves the neural network’s biomimetic performance of human attention. By incorporating matrices generated from shifted images into the self-attention mechanism, the network gains the ability to preemptively acquire information from surrounding regions. Experimental results demonstrate the superior performance of our approaches across various benchmark datasets, validating their effectiveness. Furthermore, the method was applied to patient kidney datasets collected from hospitals for diabetes diagnosis, where they achieved high accuracy with significantly reduced computational demands. This advancement showcases the potential of our methods in the field of biomimetics, aligning well with the goals of developing innovative bioinspired diagnostic tools. Full article

Convolutional neural networks have achieved excellent results in image denoising; however, there are still some problems: (1) The majority of single-branch models cannot fully exploit the image features and often suffer from the loss of information. (2) Most of the deep CNNs have inadequate edge feature extraction and saturated performance problems. To solve these problems, this paper proposes a two-branch convolutional image denoising network based on nonparametric attention and multiscale feature fusion, aiming to improve the denoising performance while better recovering the image edge and texture information. Firstly, ordinary convolutional layers were used to extract shallow features of noise in the image. Then, a combination of two-branch networks with different and complementary structures was used to extract deep features from the noise information in the image to solve the problem of insufficient feature extraction by the single-branch network model. The upper branch network used densely connected blocks to extract local features of the noise in the image. The lower branch network used multiple dilation convolution residual blocks with different dilation rates to increase the receptive field and extend more contextual information to obtain the global features of the noise in the image. It not only solved the problem of insufficient edge feature extraction but also solved the problem of the saturation of deep CNN performance. In this paper, a nonparametric attention mechanism is introduced in the two-branch feature extraction module, which enabled the network to pay attention to and learn the key information in the feature map, and improved the learning performance of the network. The enhanced features were then processed through the multiscale feature fusion module to obtain multiscale image feature information at different depths to obtain more robust fused features. Finally, the shallow features and deep features were summed using a long jump join and were processed through an ordinary convolutional layer and output to obtain a residual image. In this paper, Set12, BSD68, Set5, CBSD68, and SIDD are used as a test dataset to which different intensities of Gaussian white noise were added for testing and compared with several mainstream denoising methods currently available. The experimental results showed that this paper’s algorithm had better objective indexes on all test sets and outperformed the comparison algorithms. The method in this paper not only achieved a good denoising effect but also effectively retained the edge and texture information of the original image. The proposed method provided a new idea for the study of deep neural networks in the field of image denoising. Full article

The Holy Cross Mountains represent an isolated outcrop of Palaeozoic rocks located in the Trans-European Suture Zone, which is the boundary between the Precambrian East European Craton and Phanerozoic mobile belts of South-Western Europe. Despite extensive structural history studies, high-resolution seismic profiling has not been applied to this region until now. This research introduces near-surface seismic imaging of the Holy Cross Fault, separating two tectonic units of different stratigraphic and deformation history. In our study, we utilize a carefully designed weight drop source survey with 5 m shot and receiver spacing and 4.5 Hz geophones. The imaging technique, combining seismic reflection profiling and travel time tomography, reveals detailed fault geometries down to 400 m. Precise data processing, including static corrections and noise attenuation, significantly enhanced signal-to-noise ratio and seismic resolution. Furthermore, the paper discusses various fault imaging techniques with their shortcomings. The data reveal a complex network of intersecting fault strands, confirming general thrust fault geometry of the fault system, that align with the region’s tectonic evolution. These findings enhance understanding of the Holy Cross Mountains’ structural framework and provide valuable reference data for future studies of similar tectonic environments. Full article

To obtain accurate blackbody temperature, emissivity, and waveband measurements, an energy-domain infrared nonuniformity method based on unsupervised learning is proposed. This method exploits the inherent physical correlation within the calibration dataset and sets the average predicted energy-domain value of the same blackbody temperature as the learning goal. Then, the coefficients of the model are learned without theoretical radiance labels by leveraging clustering-based unsupervised learning methodologies. Finally, several experiments are performed on a mid-wave infrared system. The results show that the trained correction network is uniform and produces stable outputs when the integration time and attenuator change within the optimal dynamic range. The maximum change in the image corrected using the proposed algorithm was 1.29%. Full article

In protected agriculture, accurately identifying the key growth stages of tomatoes plays a significant role in achieving efficient management and high-precision production. However, traditional approaches often face challenges like non-standardized data collection, unbalanced datasets, low recognition efficiency, and limited accuracy. This paper proposes an innovative solution combining generative adversarial networks (GANs) and deep learning techniques to address these challenges. Specifically, the StyleGAN3 model is employed to generate high-quality images of tomato growth stages, effectively augmenting the original dataset with a broader range of images. This augmented dataset is then processed using a Vision Transformer (ViT) model for intelligent recognition of tomato growth stages within a protected agricultural environment. The proposed method was tested on 2723 images, demonstrating that the generated images are nearly indistinguishable from real images. The combined training approach incorporating both generated and original images produced superior recognition results compared to training with only the original images. The validation set achieved an accuracy of 99.6%, while the test set achieved 98.39%, marking improvements of 22.85%, 3.57%, and 3.21% over AlexNet, DenseNet50, and VGG16, respectively. The average detection speed was 9.5 ms. This method provides a highly effective means of identifying tomato growth stages in protected environments and offers valuable insights for improving the efficiency and quality of protected crop production. Full article

Evaluating the results of image denoising algorithms in Computed Tomography (CT) scans typically involves several key metrics to assess noise reduction while preserving essential details. Full Reference (FR) quality evaluators are popular for evaluating image quality in denoising CT scans. There is limited information about using Blind/No Reference (NR) quality evaluators in the medical image area. This paper shows the previously utilized Natural Image Quality Evaluator (NIQE) in CT scans; this NIQE is commonly used as a photolike image evaluator and provides an extensive assessment of the optimum NIQE setting. The result was obtained using the library of good images. Most are also part of the Convolutional Neural Network (CNN) training dataset against the testing dataset, and a new dataset shows an optimum patch size and contrast levels suitable for the task. This evidence indicates a possibility of using the NIQE as a new option in evaluating denoised quality to find improvement or compare the quality between CNN models. Full article

This study proposed a vision-based underwater vertical docking guidance and positioning method to address docking control challenges for human-operated vehicles (HOVs) and unmanned underwater vehicles (UUVs) under complex underwater visual conditions. A cascaded detection and positioning strategy incorporating fused active and passive markers enabled real-time detection of the relative position and pose between the UUV and docking station (DS). A novel deep learning-based network model, YOLO-D, was developed to detect docking markers in real time. YOLO-D employed the Adaptive Kernel Convolution Module (AKConv) to dynamically adjust the sample shapes and sizes and optimize the target feature detection across various scales and regions. It integrated the Context Aggregation Network (CONTAINER) to enhance small-target detection and overall image accuracy, while the bidirectional feature pyramid network (BiFPN) facilitated effective cross-scale feature fusion, improving detection precision for multi-scale and fuzzy targets. In addition, an underwater docking positioning algorithm leveraging multiple markers was implemented. Tests on an underwater docking markers dataset demonstrated that YOLO-D achieved a detection accuracy of [email protected] to 94.5%, surpassing the baseline YOLOv11n with improvements of 1.5% in precision, 5% in recall, and 4.2% in [email protected]. Pool experiments verified the feasibility of the method, achieving a 90% success rate for single-attempt docking and recovery. The proposed approach offered an accurate and efficient solution for underwater docking guidance and target detection, which is of great significance for improving the safety of docking. Full article

The current process of embryo selection in in vitro fertilization is based on morphological criteria; embryos are manually evaluated by embryologists under subjective assessment. In this study, a deep learning-based pipeline was developed to classify the viability of embryos using combined inputs, including microscopic images of embryos and additional features, such as patient age and developed pseudo-features, including a continuous interpretation of Istanbul grading scores by predicting the embryo stage, inner cell mass, and trophectoderm. For viability prediction, convolution-based transferred learning models were employed, multiple pretrained models were compared, and image preprocessing techniques and hyperparameter optimization via Optuna were utilized. In addition, a custom weight was trained using a self-supervised learning framework known as the Simple Framework for Contrastive Learning of Visual Representations (SimCLR) in cooperation with generated images using generative adversarial networks (GANs). The best model was developed from the EfficientNet-B0 model using preprocessed images combined with pseudo-features generated using separate EfficientNet-B0 models, and optimized by Optuna to tune the hyperparameters of the models. The designed model’s F1 score, accuracy, sensitivity, and area under curve (AUC) were 65.02%, 69.04%, 56.76%, and 66.98%, respectively. This study also showed an advantage in accuracy and a similar AUC when compared with the recent ensemble method. Full article

The development of deep learning has led to the proposal of various models for human activity recognition (HAR). Convolutional neural networks (CNNs), initially proposed for computer vision tasks, are examples of models applied to sensor data. Recently, high-performing models based on Transformers and multi-layer perceptrons (MLPs) have also been proposed. When applying these methods to sensor data, we often initialize hyperparameters with values optimized for image processing tasks as a starting point. We suggest that comparable accuracy could be achieved with fewer parameters for sensor data, which typically have lower dimensionality than image data. Reducing the number of parameters would decrease memory requirements and computational complexity by reducing the model size. We evaluated the performance of two MLP-based models, MLP-Mixer and gMLP, by reducing the values of hyperparameters in their MLP layers from those proposed in the respective original papers. The results of this study suggest that the performance of MLP-based models is positively correlated with the number of parameters. Furthermore, these MLP-based models demonstrate improved computational efficiency for specific HAR tasks compared to representative CNNs. Full article

Generative adversarial networks (GANs) have demonstrated remarkable performance in various fashion-related applications, including virtual try-ons, compatible clothing recommendations, fashion editing, and the generation of fashion items. Despite this progress, limited research has addressed the specific challenge of generating a compatible fashion item with an ensemble consisting of distinct categories, such as tops, bottoms, and shoes. In response to this gap, we propose a novel GANs framework, termed Deep Fashion Designer Generative Adversarial Networks (DFDGAN), designed to address this challenge. Our model accepts a series of source images representing different fashion categories as inputs and generates a compatible fashion item, potentially from a different category. The architecture of our model comprises several key components: an encoder, a mapping network, a generator, and a discriminator. Through rigorous experimentation, we benchmark our model against existing baselines, validating the effectiveness of each architectural choice. Furthermore, qualitative results indicate that our framework successfully generates fashion items compatible with the input items, thereby advancing the field of fashion item generation. Full article

In ancient historical ceramics, for various reasons, some problems such as dirt and damage inevitably occur, and necessary repair work must be carried out. Throughout ceramics restoration work, the selection and use of materials are very important. Thus, it is necessary to explore the use of modern intelligent algorithms to assist the selection and application of restoration materials during the whole restoration process, in order to improve the effectiveness of ancient ceramics restoration. In this study, convolutional neural network (CNNs) technology and a machine learning (ML) algorithm were applied to images of ceramics for the defect identification and repair of ancient ceramics, aided by additive manufacturing (AM). The simulation results show that the recall of this algorithm for AM ancient ceramics image recognition was improved by 19.68%. In order to enhance the restoration effects on ancient ceramics, it is necessary to enhance their restoration by expanding the use of digital technology, with the intent to maintain the advantages of traditional handicrafts. Therefore, we should review experiences in the restoration of ancient ceramics, introduce digital technology according to specific needs, and enhance the advanced nature of restoration work. Full article