Search

Optical synapses offer a promising solution to the high energy consumption of von Neumann architectures. Despite significant research, existing photoconductivity modulation methods are typically unidirectional, and inhibitory behavior still depends on electrical stimulation. To address this, a two‐terminal planar fully optically modulated synapse device based on a ZnAlSnO/SnS heterostructure, demonstrating bidirectional optical response is presented. This device exhibits an excitatory postsynaptic current (EPSC) when exposed to 370 nm UV light and generates an inhibitory postsynaptic current (IPSC) under 630 nm red light. Continuous potentiation and depression stimuli reveals the stability of fully optically modulated artificial synapses. Leveraging its fully optically modulated conductance, a three‐layer artificial neural network is implemented for handwritten digit and clothing recognition, achieving accuracies of 91.12% and 78.22%, respectively. Additionally, based on its unique electrical response to UV light pulse, the development process of the Polaroid camera is well simulated. This work not only enriches the content of optical synapses, but also contributes to advancements in artificial intelligence, brain‐like computing, and image‐processing technologies. [ABSTRACT FROM AUTHOR]

• Understanding plastic litter in cities is crucial to preventing marine pollution. • Citizen science is suitable for long-term, extensive data collection. • Despite human error, ∼30 % of data could be used to visualize and quantify litter. • Litter in cities was studied using Pirika and deep learning-based image processing. • Trained models exhibited high precision and recall in classifying litter types. Cities are a major source of litter pollution. Determination of the abundance and composition of plastic litter in cities is imperative for effective pollution management, environmental protection, and sustainable urban development. Therefore, here, a multidisciplinary approach to quantify and classify the abundance of litter in urban environments is proposed. In the present study, litter data collection was integrated via the Pirika smartphone application and conducted image analysis based on deep learning. Pirika was launched in May 2018 and, to date, has collected approximately one million images. Visual classification revealed that the most common types of litter were cans, plastic bags, plastic bottles, cigarette butts, cigarette boxes, and sanitary masks, in that order. The top six categories accounted for approximately 80 % of the total, whereas the top three categories accounted for more than 60 % of the total imaged litter. A deep-learning image processing algorithm was developed to automatically identify the top six litter categories. Both precision and recall derived from the model were higher than 75 %, enabling proper litter categorization. The quantity of litter derived from automated image processing was also plotted on a map using location data acquired concurrently with the images by the smartphone application. Conclusively, this study demonstrates that citizen science supported by smartphone applications and deep learning-based image processing can enable the visualization, quantification, and characterization of street litter in cities. [ABSTRACT FROM AUTHOR]

Anomaly detection and localization become necessary since humans are unable to spot visual frauds. Since it differs from the normal representation of shapes, colors, textures, size, and location, it does not have the potential to be employed in such practical applications. Hence, the automatic anomaly detection and localization framework is suggested for supporting situations like industrial systems, healthcare systems and so on. The detection and localization are the most intriguing and challenging concerns in image processing. In general, anomalies can manifest themselves in diverse ways. Detection is the process of providing information about whether an image contains modifications or not. On the other hand, localization is defined as locating the anomalies in images. Several traditional models have been deployed, but they still lack such constraints to evade performance enhancement. To sort out this issue, a novel adaptive method is recommended for anomaly detection and localization in images. Initially, the source images are acquired from standard public data sources. Once the required images are collected, such abnormal or anomalous activities are detected by adopting the new method known as Adaptive Multiscale Attention-based DenseNet (AMA-DeNet), where the hyperparameters are tuned by a hybrid algorithm known as the Hybrid Chimp Grasshopper Optimization Algorithm (HCGOA). Subsequently, the final stage is localizing the anomalies in the detected images. This is to be accomplished by using the Cascaded Variational Autoencoder (CVA), in which parameters are optimally chosen by HCGOA. After implementation, the experimental results are computed across diverse validating measures. Hence, the extensive results elucidate that the recommended model contains the potential to detect the abnormalities in the images accurately, thereby enhancing the efficiency of the new system. [ABSTRACT FROM AUTHOR]

Urban public safety management relies heavily on video surveillance systems, which provide crucial visual data for resolving a wide range of incidents and controlling unlawful activities. Traditional methods for target detection predominantly employ a two-stage approach, focusing on precision in identifying objects such as pedestrians and vehicles. These objects, typically sparse in large-scale, lower-quality surveillance footage, induce considerable redundant computation during the initial processing stage. This redundancy constrains real-time detection capabilities and escalates processing costs. Furthermore, transmitting raw images and videos laden with superfluous information to centralized back-end systems significantly burdens network communications and fails to capitalize on the computational resources available at diverse surveillance nodes. This study introduces DiffRank, a novel preprocessing method for fixed-angle video imagery in urban surveillance. The method strategically generates candidate regions during preprocessing, thereby reducing redundant object detection and improving the efficiency of the detection algorithm. Drawing upon change detection principles, a background feature learning approach utilizing shallow features has been developed. This approach prioritizes learning the characteristics of fixed-area backgrounds over direct background identification. As a result, alterations in ROI are efficiently discerned using computationally efficient shallow features, markedly accelerating the generation of proposed Regions of Interest (ROIs) and diminishing the computational demands for subsequent object detection and classification. Comparative analysis on various public and private datasets illustrates that DiffRank, while maintaining high accuracy, substantially outperforms existing baselines in terms of speed, particularly with larger image sizes (e.g., an improvement exceeding 300 % at 1920×1080 resolution). Moreover, the method demonstrates enhanced robustness compared to baseline methods, efficiently disregarding static targets like mannequins in display windows. The advancements in candidate area preprocessing enable a balanced approach between detection accuracy and overall detection speed, making the algorithm highly applicable for real-time on-site analysis in edge computing scenarios and cloud-edge collaborative computing environments. [ABSTRACT FROM AUTHOR]

Arabidopsis thaliana sepals are excellent models for analyzing growth of entire organs due to their relatively small size, which can be captured at a cellular resolution under a confocal microscope. To investigate how differential growth of connected cell layers generate unique organ morphologies, it is necessary to live-image deep into the tissue. However, imaging deep cell layers of the sepal (or plant tissues in general) is practically challenging. Image processing is also difficult due to the low signal-to-noise ratio of the deeper tissue layers, an issue mainly associated with live imaging datasets. Addressing some of these challenges, we provide an optimized methodology for live imaging sepals, and subsequent image processing. For live imaging early-stage sepals, we found that the use of a bright fluorescent membrane marker, coupled with increased laser intensity and an enhanced Z- resolution produces high-quality images suitable for downstream image processing. Our optimized parameters allowed us to image the bottommost cell layer of the sepal (inner epidermal layer) without compromising viability. We used a 'voxel removal' technique to visualize the inner epidermal layer in MorphoGraphX image processing software. We also describe the MorphoGraphX parameters for creating a 2.5D mesh surface for the inner epidermis. Our parameters allow for the segmentation and parent tracking of individual cells through multiple time points, despite the weak signal of the inner epidermal cells. While we have used sepals to illustrate our approach, the methodology will be useful for researchers intending to live-image and track growth of deeper cell layers in 2.5D for any plant tissue. [ABSTRACT FROM AUTHOR]

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fabric pilling can significantly affect the usability and appearance of fabrics; making the evaluation of pilling grades a crucial aspect of textile quality inspection. Currently, manual visual inspection is the mainstream strategy in the industry for assessing pilling, but this method suffers from low efficiency and inconsistent accuracy. Therefore, there is a need for a more precise and efficient method to evaluate textile pilling grades. In this paper, we propose an objective system for assessing fabric pilling grades using a deep learning model in conjunction with a gradient boosting decision tree classification algorithm. The system comprises a multi-light source fabric image acquisition setup, an Attention-enhanced UNet model, and a gradient boosting decision tree classifier. The process begins with capturing fabric images, which are then segmented using the Attention-enhanced UNet model. This model effectively extracts pilling features, including the number of pills, the pilling area, and the pilling coverage ratio. Our experimental results show that this segmentation method outperforms traditional filtering and edge detection algorithms in terms of efficiency. The attention mechanism integrated into the UNet model significantly enhances the segmentation performance, particularly for fabric pilling. By combining the extracted features as input for the fabric evaluation algorithm, our proposed method achieves an impressive classification accuracy of 98.47% in objectively evaluating fabric pilling grades. This approach offers a substantial improvement in both the accuracy and efficiency of fabric pilling grade assessment. [ABSTRACT FROM AUTHOR]

Flame temperature field measurement has always been a key topic in combustion research, which is of great significance for combustion state diagnosis and fuel combustion optimization. Deep learning technology exploits its superior nonlinear ability to rapidly reconstruct the three-dimensional (3D) temperature field of flames from flame light-field images. However, existing algorithms have problems with complex networks, poor noise resistance and low reconstruction accuracy. This paper proposes a lightweight 3D flame temperature field reconstruction algorithm based on an improved MobileNet that combines residuals and spatial attention mechanisms. This method basically achieves a balance between low complexity and high accuracy and has good noise resistance performance. Simulation results show that the average relative error of temperature field reconstruction on the noise-free unimodal flame dataset is only 0.022%, and its computational complexity is only one-tenth of the existing CNN. The noise simulation experiment shows that this method has good noise resistance performance. The maximum relative error and the average relative error at Gaussian white noise standard deviation σ = 0.15 are only 2.91% and 0.27%, respectively. [ABSTRACT FROM AUTHOR]

Modern bioimaging core facilities at research institutions are essential for managing and maintaining high‐end instruments, providing training and support for researchers in experimental design, image acquisition and data analysis. An important task for these facilities is the professional management of complex multidimensional bioimaging data, which are often produced in large quantity and very different file formats. This article details the process that led to successfully implementing the OME Remote Objects system (OMERO) for bioimage‐specific research data management (RDM) at the Core Facility Cellular Imaging (CFCI) at the Technische Universität Dresden (TU Dresden). Ensuring compliance with the FAIR (findable, accessible, interoperable, reusable) principles, we outline here the challenges that we faced in adapting data handling and storage to a new RDM system. These challenges included the introduction of a standardised group‐specific naming convention, metadata curation with tagging and Key–Value pairs, and integration of existing image processing workflows. By sharing our experiences, this article aims to provide insights and recommendations for both individual researchers and educational institutions intending to implement OMERO as a management system for bioimaging data. We showcase how tailored decisions and structured approaches lead to successful outcomes in RDM practices. [ABSTRACT FROM AUTHOR]

In the image analysis of the hydrophobic flocculation process of coal particles, the recognition accuracy of floc characteristic parameters is affected by bubbles, floc superposition, and floc morphology. An image processing method was studied and designed based on the PyCharm Community platform for clarity recognition and floc segmentation of coal particle floc characteristics. Firstly, the critical value of image clarity was determined to be 1.31 by using the Laplace convolution accounting method after the average gray level correction, and the fuzzy flocs whose clarity was less than the critical value were eliminated. Then, by comparing the segmentation effect of the threshold, edge, and region segmentation algorithm on the flocs, the histogram bimodal method was determined to be the best image processing segmentation method for fine coal floc collection. The fractal theory was used to verify the effect of image processing. The results showed that the surface fractal dimension of the floc image after deblurring and segmentation was maintained near 2.05, indicating that the processed image can obtain more stable and reliable floc characteristic parameters. [ABSTRACT FROM AUTHOR]

This study introduces a novel approach that addresses the limitations of existing methods by integrating 2D image processing with 3D point cloud analysis, enhanced by interpretable neural networks. Unlike traditional methods that rely on either 2D or 3D data alone, our approach leverages the complementary strengths of both data types to improve detection accuracy in environments adversely affected by welding spatter and smoke. Our system employs an improved Faster R-CNN model with a ResNet50 backbone for 2D image analysis, coupled with an innovative orthogonal plane intersection line extraction algorithm for 3D point cloud processing. By incorporating explainable components such as visualizable feature maps and a transparent region proposal network, we address the "black box" issue common in deep learning models.This architecture enables a more transparent decision-making process, providing technicians with necessary insights to understand and trust the system's outputs. The Faster-RCNN structure is designed to break down the object detection process into distinct, understandable steps, from initial feature extraction to final bounding box refinement. This fusion of 2D-3D data analysis and interpretability not only improves detection performance but also sets a new standard for transparency and reliability in automated welding systems, facilitating wider adoption in industrial applications. [ABSTRACT FROM AUTHOR]

Sandwich structures are known for their exceptional mechanical properties and widespread applications. This study integrates additive manufacturing (AM) technology, experiments, theoretical equations, and numerical simulations to investigate a novel lightweight sandwich structure with a core based on Triply Periodic Minimal Surfaces (TPMS). The core incorporates Primitive, Neovius, and Diamond structures and is designed and manufactured using AM. Three‐point bending experiments are conducted to assess bending performance, failure modes, and energy absorption capability. A numerical model is established to analyze behavior under bending loads, validated through comparison with theoretical equations and numerical simulations, focusing on stress concentration areas. A parametric study investigates the effects of skin material, thickness, and TPMS core relative density on bending performance and energy absorption capacity. Furthermore, a functionally graded core layer with a gradient change in relative density is designed to study its influence on bending performance. The parameters of the core have a decisive impact on TPMS sandwich panel performance. This study demonstrates that sandwich structures with TPMS cores can be designed to possess desirable bending performance and energy absorption capacity, providing insights for future engineering applications. Highlights: A novel TPMS sandwich structure is fabricated using 3D printing technology.The gradient relative density core is introduced.The bending performance and failure behavior of the structure are evaluated.A parametric study was conducted to investigate the effects on performance. [ABSTRACT FROM AUTHOR]

Deep learning applications have witnessed significant advancements across diverse domains, revolutionizing tasks such as image recognition, disease classification, cancer detection, natural language processing, and autonomous decision-making. However, striking a balance between performance and cost remains a fundamental challenge. Performance, which encompasses accuracy, efficiency, and effectiveness, is crucial for the real-world applicability of deep learning models. Attaining high performance often involves using resource-intensive models with intricate architectures, extensive datasets, and hyperparameter tuning. While these factors lead to improved performance, they also result in increased costs, including computational resources, time, and energy consumption. This research addresses this challenge by proposing a novel low-cost deep learning model based on Sharpened Cosine Similarity (LC-SCS) for breast cancer classification using thermal images. In our study on a DMR-IR dataset, we also utilized pre-trained models: ResNet-101, VGG-16, Inception-V3, ResNet-50, VGG-19, and Xception. The proposed LC-SCS model achieved an impressive accuracy of 94%, trailing just 4% behind the leading VGG-19 model, while maintaining a low computational cost. It achieved recall and precision scores of 0.95 each, with an F1-score of 0.94. The LC-SCS model excels in computational efficiency, demanding only 1.85 GFLOPs and 1.2 million parameters. The memory requirement is minimal at 865.35 MB, and it exhibits a latency of just 0.003 s. Additionally, the CPU execution time for prediction is 3.59 s. Comparatively, the best-performing pre-trained VGG-19 model achieved 98% accuracy but incurred significantly higher costs. The proposed LC-SCS model showcases a remarkable 298.63 times reduction in GFLOPs, a 116.31 times reduction in total parameters, a 4.57 times reduction in memory requirements for model weights, a 5 times reduction in latency, and a 3.33 times reduction in CPU execution time for prediction, thus making it as an exceptionally resource-efficient model, particularly in scenarios with limited computational resources. [ABSTRACT FROM AUTHOR]

Automatic skin lesion subtyping is a crucial step for diagnosing and treating skin cancer and acts as a first level diagnostic aid for medical experts. Although, in general, deep learning is very effective in image processing tasks, there are notable areas of the processing pipeline in the dermoscopic image regime that can benefit from refinement. Our work identifies two such areas for improvement. First, most benchmark dermoscopic datasets for skin cancers and lesions are highly imbalanced due to the relative rarity and commonality in the occurrence of specific lesion types. Deep learning methods tend to exhibit biased performance in favor of the majority classes with such datasets, leading to poor generalization. Second, dermoscopic images can be associated with irrelevant information in the form of skin color, hair, veins, etc.; hence, limiting the information available to a neural network by retaining only relevant portions of an input image has been successful in prompting the network towards learning task-relevant features and thereby improving its performance. Hence, this research work augments the skin lesion characterization pipeline in the following ways. First, it balances the dataset to overcome sample size biases. Two balancing methods, synthetic minority oversampling TEchnique (SMOTE) and Reweighting, are applied, compared, and analyzed. Second, a lesion segmentation stage is introduced before classification, in addition to a preprocessing stage, to retain only the region of interest. A baseline segmentation approach based on Bi-Directional ConvLSTM U-Net is improved using conditional adversarial training for enhanced segmentation performance. Finally, the classification stage is implemented using EfficientNets, where the B2 variant is used to benchmark and choose between the balancing and segmentation techniques, and the architecture is then scaled through to B7 to analyze the performance boost in lesion classification. From these experiments, we find that the pipeline that balances using SMOTE and uses the adversarially trained segmentation network achieves the best baseline performance of 91% classification accuracy with EfficientNet B2. Based on the scaling experiments, we find that optimal performance is reached with the B6 architecture that classifies with a 97% accuracy. Furthermore, the proposed pipeline for lesion characterization outperforms the state of the art performance on the ISIC dataset. [ABSTRACT FROM AUTHOR]

The image object recognition and detection technology are widely used in many scenarios. In recent years, big data has become increasingly abundant, and big data-driven artificial intelligence models have attracted more and more attention. Evolutionary computation has also provided a powerful driving force for the optimization and improvement of deep learning models. In this paper, we propose an image object detection method based on self-supervised and data-driven learning. Differ from other methods, our approach stands out due to its innovative use of multispectral data fusion and evolutionary computation for model optimization. Specifically, our method uniquely combines visible light images and infrared images to detect and identify image targets. Firstly, we utilize a self-supervised learning method and the AutoEncoder model to perform high-dimensional feature extraction on the two types of images. Secondly, we fuse the extracted features from the visible light and infrared images to detect and identify objects. Thirdly, we introduce a model parameter optimization method using evolutionary learning algorithms to enhance model performance. Validation on public datasets shows that our method achieves comparable or superior performance to existing methods. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) are popular in image processing but are vulnerable to adversarial attacks, which makes their deployment in security-sensitive systems risky. Adversarial attacks reduce the performance of DNNs by generating adversarial examples (AEs). In this paper, we propose a novel method called Trans-IFFT-FGSM (Transformer Inverse Finite Fourier Transform Fast Gradient Sign Method) to generate adversarial examples. Unlike others, we apply multiple steps, adding imperceptible perturbation and saving input noise information to create strong AEs, while emphasizing simplicity, efficiency, robustness through iterations, and analytical precision on specific models. We evaluate and compare perturbation generated by Trans-IFFT-FGSM and other attack methods, including FGSM, PGD, DeepFool, and C &W on ImageNet and MNIST, and evaluation results suggest that Trans-IFFT-FGSM achieves a high attack success rate (ASR) and attack accuracy. In addition, we compare Trans-IFFT-FGSM and other attack methods under the existence of a defense method, which denoises the AEs generated by these methods, and the evaluation results also suggest Trans-IFFT-FGSM outperforms other methods. [ABSTRACT FROM AUTHOR]

The field of computer vision has witnessed significant interest in the area of salient object recognition. The utilization of this technology becomes advantageous in various applications, such as image segmentation, image attention retargeting, image cropping, and image understanding. The primary challenges encountered by underwater images pertain to diminished contrast, distorted colors, and an overall suboptimal visual appearance. The present study introduces an innovative and resilient method for detecting saliency in underwater photos. The RGB picture input undergoes enhancement and is subsequently subjected to gradient domain filtration. The filtered image is subjected to a pyramid decomposition. The computation of saliency is performed on three distinct scales using a process consisting of two parallel phases. In the first stage, saliency is calculated by employing cellular automata at various scales. Initially, the filtered image is subjected to a decomposition process into superpixels. Subsequently, the k-means clustering technique is employed to calculate matrices that represent color dissimilarity and geodesic distance. The application of cellular automata follows the fusion of the matrices. The map undergoes additional optimization and filtering processes in order to achieve saliency at a specific scale. The computation of a main saliency map involves the process of scale integration. In the second stage, the computation of saliency is achieved by applying a homomorphic filter to each scale. The natural logarithm of the filtered image is computed. The spatial domain of the image undergoes a transformation to the frequency domain. The Butterworth high-pass filter is utilized. The frequency domain of the image is subsequently converted back to its spatial domain. The computation of the inverse logarithm of the image is performed. The guided filter is employed to acquire saliency on a specific scale. The computation of the secondary saliency map involves the process of scale integration. The final output is obtained by applying multiplicative fusion to both primary and secondary saliency maps. Utilizing cutting-edge methodologies, a thorough evaluation that includes both qualitative and quantitative analyses evaluates the effectiveness of the suggested strategy. In comparison to alternative state-of-the-art methodologies, the findings indicate that the suggested methodology exhibits high levels of precision and dependability. [ABSTRACT FROM AUTHOR]

In order to solve the problems of IspecHyper multi-rotor UAV hyperspectral imaging system, such as lack of data processing supporting software, large error in collecting multi-band hyperspectral data, lack of coordinates, and inability to automatically stitch. Taking the citrus planting base of Jiaolong Village, Taiping Town, Wuming District as the research area, this paper studies the hyperspectral image processing method of IspecHyper multi-rotor UAV. Firstly, the IspecHyper-VM200 imaging system was used to obtain high-definition photos and multi-band hyperspectral image data of the study area. Secondly, using high-definition photos as data sources, high-resolution UAV orthophotos were formed by PXI4D Mapper software preprocessing and ENVI software image geometric correction. Finally, the ENVI software was used to cut the distorted boundary data of multi-band hyperspectral images, and the geometric correction was completed based on the UAV orthophoto image, and then the hyperspectral reflectance image product was formed through image mosaic and spectral conversion calculation. The experimental results show that the technical method formed in this paper can effectively solve the problems of hyperspectral image processing of IspecHyper multi-rotor UAV, and provide technical reference for hyperspectral image processing of UAV. [ABSTRACT FROM AUTHOR]

Public safety is a critical concern, typically addressed through security checks at entrances of public places, involving trained officers or X-ray scanning machines to detect prohibited items. However, many places like hospitals, schools, and event centres lack such resources, risking security breaches. Even with X-ray scanners or manual checks, gaps can be exploited by individuals with malicious intent, posing significant security risks. Additionally, traditional methods, relying on manual inspections and conventional image processing techniques, are often inefficient and prone to high error rates. To mitigate these risks, we propose a real-time detection model – EnhanceNet using a customized Scale-Enhanced Pooling Network (SEP-Net) integrated into the YOLOv4. The innovative SEP-Net enhances feature representation and localization accuracy, significantly contributing to the model’s efficacy in detecting prohibited items. We annotated a custom dataset of nine classes and evaluated our models using different input sizes (608 and 416). The 608 input size achieved a mean Average Precision (mAP) of 74.10% with a detection speed of 22.3 Frames per Second (FPS). The 416 input size showed superior performance, achieving a mAP of 76.75% and a detection speed of 27.1 FPS. These demonstrate that our models are accurate and efficient, making them suitable for real-time applications. [ABSTRACT FROM AUTHOR]

In the field of image processing, common noise types include Gaussian noise, salt and pepper noise, speckle noise, uniform noise and pulse noise. Different types of noise require different denoising algorithms and techniques to maintain image quality and fidelity. Traditional image denoising methods not only remove image noise, but also result in the detail loss in the image. It cannot guarantee the clean removal of noise information while preserving the true signal of the image. To address the aforementioned issues, an image denoising method combining an improved threshold function and wavelet transform is proposed in the experiment. Unlike traditional threshold functions, the improved threshold function is a continuous function that can avoid the pseudo Gibbs effect after image denoising and improve image quality. During the process, the output image of the finite ridge wave transform is first combined with the wavelet transform to improve the denoising performance. Then, an improved threshold function is introduced to enhance the quality of the reconstructed image. In addition, to evaluate the performance of different algorithms, different densities of Gaussian noise are added to Lena images of black, white, and color in the experiment. The results showed that when adding 0.010.01 variance Gaussian noise to black and white images, the peak signal-to-noise ratio of the research method increased by 2.58dB in a positive direction. The mean square error decreased by 0.10dB. When using the algorithm for denoising, the research method had a minimum denoising time of only 13ms, which saved 9ms and 3ms compared to the hard threshold algorithm (Hard TA) and soft threshold algorithm (Soft TA), respectively. The research method exhibited higher stability, with an average similarity error fluctuating within 0.89%. The above results indicate that the research method has smaller errors and better system stability in image denoising. It can be applied in the field of digital image denoising, which can effectively promote the positive development of image denoising technology to a certain extent. [ABSTRACT FROM AUTHOR]

Stripe noise is a prevalent issue in infrared imaging systems, characterized by its distinctive directional features, which often appear as vertical lines across the image. This type of noise can significantly degrade the quality of the captured images, making it crucial to address and mitigate its effects. This paper presents an effective strategy to tackle this problem by transforming it from a 2D image issue into a 1D signal problem, enabling efficient resolution of stripes in infrared images. By understanding the characteristics of stripe noise, the proposed algorithm effectively solves the problem by first computing the column average of the noisy image, extracting stripe components from this one-dimensional signal, and effectively removing the stripes without blurring image details. This approach has been tested on numerous images with varying noise levels, demonstrating exceptional denoising performance compared to state-of-the-art methods. The results show marked improvements in visual quality, especially around edges and smooth areas, without requiring complex algorithms or iterative processes. [ABSTRACT FROM AUTHOR]

Introduction: Paediatric forearm fractures are a prevalent reason for medical consultation, often requiring diagnostic X-rays that present a risk due to ionising radiation, especially concerning given the sensitivity of children's tissues. This paper explores the efficacy of ultrasound imaging, particularly through the development of the SonoBox system, as a safer, non-ionising alternative. With emerging evidence supporting ultrasound as a viable method for fracture assessment, innovations like SonoBox will become increasingly important. Materials and methods: In our project, we want to advance ultrasound-based, contact-free, and automated cross-sectional imaging for diagnosing paediatric forearm fractures. To this end, we are building a technical platform that navigates a commercially available ultrasound probe around the extremity within a water-filled tank, utilising intelligent robot control and image processing methods to generate a comprehensive ultrasound tomogram. Safety and hygiene considerations, gender and diversity relevance, and the potential reduction of radiation exposure and examination pain are pivotal aspects of this endeavour. Results: Preliminary experiments have demonstrated the feasibility of rapidly generating ultrasound tomographies in a water bath, overcoming challenges such as water turbulence during probe movement. The SonoBox prototype has shown promising results in transmitting position data for ultrasound imaging, indicating potential for autonomous, accurate, and potentially painless fracture diagnosis. The project outlines further goals, including the construction of prototypes, validation through patient studies, and development of a hygiene concept for clinical application. Conclusion: The SonoBox project represents a significant step forward in paediatric fracture diagnostics, offering a safer, more comfortable alternative to traditional X-ray imaging. By automating the imaging process and removing the need for direct contact, SonoBox has the potential to improve clinical efficiency, reduce patient discomfort, and broaden the scope of ultrasound applications. Further research and development will focus on validating its effectiveness in clinical settings and exploring its utility in other medical and veterinary applications. [ABSTRACT FROM AUTHOR]

Black ice is responsible for dangerous road-related incidents that can cause collisions and harm vehicle drivers and pedestrians. Visual examination and weather forecasts are two standard traditional methods for detecting black ice on roads, but they are often inaccurate and may not deliver the vehicle driver with up-to-date information on road conditions. The evolution of Industry 4.0 enabling technologies such as wireless sensor network (WSN), Internet of Things (IoT), cloud computing, and machine learning (ML) has been capable of detecting events in real time. This study aims to analyse the integration of the WSN, IoT, ML, and image processing for black ice detection. The qualitative research method is followed in this study, where the problems of black ice detection are studied. Following this, the role of Industry 4.0 enabling technologies is analyzed in detail for black ice detection. According to the study, we can detect black ice using different methods, but some methods need to be refined if we talk about the prediction. By merging different technologies, we can improve the overall architecture and create an algorithm that works with images and physical variables like temperature, humidity, due point, and road temperature, which were responsible for black ice formation, and predict the chances of black ice formation by training the system. [ABSTRACT FROM AUTHOR]

AbstractIn this experimental study, we delve into the performance of an active mixer that utilizes liquid metal droplets. Our mixer configuration follows an innovative Y-type design, where two liquid metal-based pumping mechanisms operate within the minichannel inlet branches. By applying alternating current voltage to both sides of the liquid metal, we induce a surface tension gradient, propelling the fluid from the reservoirs toward the minichannel. Notably, the two entering liquids are distinctly colored, allowing us to quantify mixing using a Mixing Index (MI) definition and image processing techniques. Our investigation centers on four key variables governing mixer performance: applied voltage, liquid metal droplet diameter, input angle between the branches, and minichannel width. Given the experimental nature of our research, we employ a central composite design method within the framework of design of experiments (DoE). From our obtained experimental results, we establish correlations between MI and the other variables. Our examination of the four mentioned parameters revealed that liquid metal droplet diameter exerts the most significant influence on the mixing index. Following this, in descending order of impact, we find applied voltage, input angle, and channel width. In the optimal dimensions of our mixer, we achieve a remarkable maximum MI of 0.867. [ABSTRACT FROM AUTHOR]

This study aims to evaluate the applicability of the high-resolution WaveFront Phase Imaging Sensor (WFPI) in eyes with Fuchs' Endothelial Corneal Dystrophy (FECD) through qualitative and quantitative analysis using a custom-designed Automatic Guttae Detection Method (AGDM). The ocular phase was measured using the t · eyede aberrometer and then was processed to obtain its High-Pass Filter Map (HPFM). The subjects were pathological and healthy patients from the Fundación Jiménez-Díaz Hospital (Madrid, Spain). The AGDM was developed and applied in pupils with 3 and 5 mm of diameter. A set of metrics were extracted and evaluated like the Root-Mean-Square error (RMS), Number of guttae, Guttae Area, and Area of Delaunay Triangulation (DT). Finally, a Support Vector Machine (SVM) model was trained to classify between pathological and healthy eyes. Quantitatively, the HPFM reveals a dark spots pattern according to the ophthalmologist's description of the slit-lamp examination of guttae distribution. There were significant statistical differences in all the metrics when FECD and Healthy groups were compared using the same pupil size; but comparing both pupil sizes for the same group there were significant differences in most of the variables. This sensor is a value tool to objectively diagnose and monitor this pathology through wavefront phase changes. [ABSTRACT FROM AUTHOR]

Text‐based hair design (TBHD) represents an innovative approach that utilizes text instructions for crafting hairstyle and colour, renowned for its flexibility and scalability. However, enhancing TBHD algorithms to improve generation quality and editing accuracy remains a current research difficulty. One important reason is that existing models fall short in alignment and fusion designs. Therefore, we propose a new layered multimodal fusion network called ETBHD‐HMF, which decouples the input image and hair text information into layered hair colour and hairstyle representations. Within this network, the channel enhancement separation (CES) module is proposed to enhance important signals and suppress noise for text representation obtained from CLIP, thus improving generation quality. Based on this, we develop the weighted mapping fusion (WMF) sub‐networks for hair colour and hairstyle. This sub‐network applies the mapper operations to input image and text representations, acquiring joint information. The WMF then selectively merges image representation and joint information from various style layers using weighted operations, ultimately achieving fine‐grained hairstyle designs. Additionally, to enhance editing accuracy and quality, we design a modality alignment loss to refine and optimize the information transmission and integration of the network. The experimental results of applying the network to the CelebA‐HQ dataset demonstrate that our proposed model exhibits superior overall performance in terms of generation quality, visual realism, and editing accuracy. ETBHD‐HMF (27.8 PSNR, 0.864 IDS) outperformed HairCLIP (26.9 PSNR, 0.828 IDS), with a 3% higher PSNR and a 4% higher IDS. [ABSTRACT FROM AUTHOR]

Reversible solid oxide cells (r -SOCs) are regarded as a solution form of clean energy generation towards a green hydrogen energy transition. However, during transportation, installation, and operation, they are required to withstand dynamic conditions as they face thermal, mechanical, and vibrational effects. Assessing the interplay of the thermomechanical and dynamical impacts on r-SOC materials during the mode-switch from electrolysis to fuel cell operation is the subject of this current comprehensive study. Advanced FEM-based homogenisation techniques have been harnessed in predicting and evaluating the detailed transients during static and dynamic loading. The intricate 3D thermal profiles throughout the transient reversible dual-modus operation from a typical r-SOC study have been derived using advanced image processing. Orthotropic material properties were incorporated into a unified macroscopic scale model by deriving the complex 3D microstructure geometry characteristics of the cell materials and component layers. The comprehensive thermomechanical and pre-stressed modal analysis results showed that the static and dynamic forces in fuel cell mode are more pronounced, whereas, in electrolysis operation, the dynamical behaviour highly depends on geometrical and operating conditions. Smaller component size shows higher natural frequencies and more intense vibration, leading to higher deformation attributed to complex mode shapes and reduced flexural rigidity. These insights are essential for optimizing r-SOC design parameters, enhancing their dynamic and structural reliability throughout their dual-mode operation lifespan. • Influence of cell size and thickness on static and dynamic r-SOC behaviour. • 3D physical r-SOC microstructure model generation and virtually characterisation. • Thermal field derivation using data recognition and image processing techniques. • 3D thermomechanical stresses, natural frequencies, and mode shapes are determined. • Comparison of thermomechanical and dynamic effects on reversible operation. [ABSTRACT FROM AUTHOR]

The need for effective and precise detection technologies to lessen the impact of pests on agricultural output is a global concern. This research introduces a new method for detecting pests using image processing techniques and artificial neural networks (ANNs). A strong solution that can identify pests in different agricultural contexts is offered by our suggested technique, which uses learning and image analysis. Artificial neural networks (ANNs) allow for the training of specialised models that can identify different types of pests using visual features collected from digital photos. In addition, picture preparation methods are used to boost model performance and feature extraction. Extensive studies on real-world datasets reveal that the suggested method outperforms standard pest detection approaches in terms of efficiency and accuracy, proving its efficacy. A dependable and automated approach for early pest identification is offered by this study, which advances the area of precision agriculture. This allows for earlier intervention and minimises crop loss. We use artificial neural networks (ANN) because of their capacity to learn complicated patterns straight from picture data; this method is based on the latest developments in deep learning as well as image processing. Additionally, input pictures are preprocessed using feature extraction methods such morphological operations and histogram equalisation to successfully decrease noise and improve the recovered features' discriminative strength. In order to test how well our method works, we use a wide range of datasets that include different types of pests and their environments. Achieving excellent accuracy rates in pest identification tasks, the results show that our technology is resilient and scalable across multiple agricultural situations. Additionally, we contrast our technique with more conventional ways to pest identification, such as chemical-based methods and human inspection, to demonstrate the benefits of automation and efficiency that our system provides. Our research highlights the incredible power of AI and image processing to transform pest control approaches. This might lead to more resilient and sustainable agricultural systems that can withstand new threats. [ABSTRACT FROM AUTHOR]

As generative models become more advanced and essential, interest in using these models for image editing is growing. Nevertheless, conventional image editing methods still have many problems and can alter the intrinsic properties (e.g. geometry) of an object during the editing process. In this article, a novel geometry‐preserved image editing method is presented, where key points, keyframe, or canny edges are utilized as inputs for geometric constraints. A text prompt is fed into the inversion pipeline along with the input image and key points/keyframes/canny for editing. Then, new images are generated based on the editing pipeline of the denoising diffusion implicit model. Experiments demonstrate that the method outperforms its baselines. [ABSTRACT FROM AUTHOR]

The conjugate gradient (CG) directions are among the important components of the CG algorithms. These directions have proven their effectiveness in many applications—more specifically, in image processing due to their low memory requirements. In this study, we derived a new conjugate gradient coefficient based on the famous quadratic model. The derived algorithm is distinguished by its global convergence and essential descent properties, ensuring robust performance across diverse scenarios. Extensive numerical testing on image restoration and unconstrained optimization problems have demonstrated that the new formulas significantly outperform existing methods. Specifically, the proposed conjugate gradient scheme has shown superior performance compared to the traditional Fletcher–Reeves (FR) conjugate gradient method. This advancement not only enhances computational efficiency on unconstrained optimization problems, but also improves the accuracy and quality of image restoration, making it a highly valuable tool in the field of computational imaging and optimization. [ABSTRACT FROM AUTHOR]

As a fundamental element of the transportation system, traffic signs are widely used to guide traffic behaviors. In recent years, drones have emerged as an important tool for monitoring the conditions of traffic signs. However, the existing image processing technique is heavily reliant on image annotations. It is time consuming to build a high-quality dataset with diverse training images and human annotations. In this paper, we introduce the utilization of Vision–language Models (VLMs) in the traffic sign detection task. Without the need for discrete image labels, the rapid deployment is fulfilled by the multi-modal learning and large-scale pretrained networks. First, we compile a keyword dictionary to explain traffic signs. The Chinese national standard is used to suggest the shape and color information. Our program conducts Bootstrapping Language-image Pretraining v2 (BLIPv2) to translate representative images into text descriptions. Second, a Contrastive Language-image Pretraining (CLIP) framework is applied to characterize not only drone images but also text descriptions. Our method utilizes the pretrained encoder network to create visual features and word embeddings. Third, the category of each traffic sign is predicted according to the similarity between drone images and keywords. Cosine distance and softmax function are performed to calculate the class probability distribution. To evaluate the performance, we apply the proposed method in a practical application. The drone images captured from Guyuan, China, are employed to record the conditions of traffic signs. Further experiments include two widely used public datasets. The calculation results indicate that our vision–language model-based method has an acceptable prediction accuracy and low training cost. [ABSTRACT FROM AUTHOR]

Potholes and other road surface damages pose significant risks to vehicles and traffic safety. The current methods of in situ visual inspection for potholes or cracks are inefficient, costly, and hazardous. Therefore, there is a pressing need to develop automated systems for assessing road surface conditions, aiming to efficiently and accurately reconstruct, recognize, and locate potholes. In recent years, various methods utilizing (a) computer vision, (b) three-dimensional (3D) point clouds, or (c) smartphone data have been employed to map road surface quality conditions. Machine learning and deep learning techniques have increasingly enhanced the performance of these methods. This review aims to provide a comprehensive overview of cutting-edge computer vision and machine learning algorithms for pothole detection. It covers topics such as sensing systems for acquiring two-dimensional (2D) and 3D road data, classical algorithms based on 2D image processing, segmentation-based algorithms using 3D point cloud modeling, machine learning, deep learning algorithms, and hybrid approaches. The review highlights that hybrid methods combining traditional image processing and advanced machine learning techniques offer the highest accuracy in pothole detection. Machine learning approaches, particularly deep learning, demonstrate superior adaptability and detection rates, while traditional 2D and 3D methods provide valuable baseline techniques. By reviewing and evaluating existing vision-based methods, this paper clarifies the current landscape of pothole detection technologies and identifies opportunities for future research and development. Additionally, insights provided by this review can inform the design and implementation of more robust and effective systems for automated road surface condition assessment, thereby contributing to enhanced roadway safety and infrastructure management. [ABSTRACT FROM AUTHOR]

In maritime transportation, a ship's draft survey serves as a primary method for weighing bulk cargo. The accuracy of the ship's draft reading determines the fairness of bulk cargo transactions. Human visual-based draft reading methods face issues such as safety concerns, high labor costs, and subjective interpretation. Therefore, some image processing methods are utilized to achieve automatic draft reading. However, due to the limitations in the spectral characteristics of RGB images, existing image processing methods are susceptible to water surface environmental interference, such as reflections. To solve this issue, we obtained and annotated 524 multispectral images of a ship's draft as the research dataset, marking the first application of integrating NIR information and RGB images for automatic draft reading tasks. Additionally, a dual-branch backbone named BIF is proposed to extract and combine spectral information from RGB and NIR images. The backbone network can be combined with the existing segmentation head and detection head to perform waterline segmentation and draft detection. By replacing the original ResNet-50 backbone of YOLOv8, we reached a mAP of 99.2% in the draft detection task. Similarly, combining UPerNet with our dual-branch backbone, the mIoU of the waterline segmentation task was improved from 98.9% to 99.3%. The inaccuracy of the draft reading is less than ±0.01 m, confirming the efficacy of our method for automatic draft reading tasks. [ABSTRACT FROM AUTHOR]

Digital photogrammetry has attracted widespread attention in the field of geotechnical and geological surveys due to its low-cost, ease of use, and contactless mode. In this work, with the purpose of studying the progressive block surficial detachments of a landslide, we developed a monitoring system based on fixed multi-view time-lapse cameras. Thanks to a newly developed photogrammetric algorithm based on the comparison of photo sequences through a structural similarity metric and the computation of the disparity map of two convergent views, we can quickly detect the occurrence of collapse events, determine their location, and calculate the collapse volume. With the field data obtained at the Perarolo landslide site (Belluno Province, Italy), we conducted preliminary tests of the effectiveness of the algorithm and its accuracy in the volume calculation. The method of quickly and automatically obtaining the collapse information proposed in this paper can extend the potential of landslide monitoring systems based on videos or photo sequence and it will be of great significance for further research on the link between the frequency of collapse events and the driving factors. [ABSTRACT FROM AUTHOR]

Semantic segmentation is currently a hot topic in remote sensing image processing. There are extensive applications in land planning and surveying. Many current studies combine Convolutional Neural Networks (CNNs), which extract local information, with Transformers, which capture global information, to obtain richer information. However, the fused feature information is not sufficiently enriched and it often lacks detailed refinement. To address this issue, we propose a novel method called the Multi-View Feature Fusion and Rich Information Refinement Network (MFRNet). Our model is equipped with the Multi-View Feature Fusion Block (MAFF) to merge various types of information, including local, non-local, channel, and positional information. Within MAFF, we introduce two innovative methods. The Sliding Heterogeneous Multi-Head Attention (SHMA) extracts local, non-local, and positional information using a sliding window, while the Multi-Scale Hierarchical Compressed Channel Attention (MSCA) leverages bar-shaped pooling kernels and stepwise compression to obtain reliable channel information. Additionally, we introduce the Efficient Feature Refinement Module (EFRM), which enhances segmentation accuracy by interacting the results of the Long-Range Information Perception Branch and the Local Semantic Information Perception Branch. We evaluate our model on the ISPRS Vaihingen and Potsdam datasets. We conducted extensive comparison experiments with state-of-the-art models and verified that MFRNet outperforms other models. [ABSTRACT FROM AUTHOR]

This study is structured to address the problem of mapping the bottom of shallow and ultra-shallow inland water bodies using high-resolution satellite imagery. These environments, with their diverse distribution of optically relevant components, pose a challenge to traditional mapping methods. The study was conducted on several research issues, each focusing on a specific aspect of the SDB, related to the selection of spectral bands and regression models, regression models creation, evaluation of the influence of the number and spatial distribution of reference soundings, and assessment of the quality of the bathymetric surface, with a focus on microtopography. The study utilized basic empirical techniques, incorporating high-precision reference data acquired via an unmanned surface vessel (USV) integrated with a single-beam echosounder (SBES), and Global Navigation Satellite System (GNSS) receiver measurements. The performed investigation allowed the optimization of a methodology for bathymetry acquisition of such areas by identifying the impact of individual processing components. The first results indicated the usefulness of the proposed approach, which can be confirmed by the values of the obtained RMS errors of elaborated bathymetric surfaces in the range of up to several centimeters in some study cases. The work also points to the problematic nature of this type of study, which can contribute to further research into the application of remote sensing techniques for bathymetry, especially during acquisition in optically complex waters. [ABSTRACT FROM AUTHOR]

Built heritage materials assessment is an important task for planning and managing future conservation works. The uniqueness of each historical building makes reconnaissance operations more complex and specific for every single building. In the past, visual inspection and invasive techniques were widely used to investigate surface materials. Non-destructive techniques (NDTs) such as multi-band photogrammetry and remote sensing can help to assess the buildings without any contact with the investigated objects, restricting the disruptive tests on limited areas and reducing the testing time and costs of the surveys. This paper presents the results obtained using multi-band images acquired with a low-cost imaging solution after interchanging several filters, and the application of the principal components analysis (PCA) to recognize different materials of a significant historical monument. The Serranos Towers, built between 1392 and 1398, suffered several interventions in the past that affected their state of conservation with the replacement of different materials. The results of the study show the usefulness of applying PCA to distinguish different surface materials, often similar to the original ones, in a fast and efficient way to investigate and analyze our heritage legacy. [ABSTRACT FROM AUTHOR]

In view of the complexity and diversity of hyperspectral images (HSIs), the classification task has been a major challenge in the field of remote sensing image processing. Hyperspectral classification (HSIC) methods based on neural architecture search (NAS) is a current attractive frontier that not only automatically searches for neural network architectures best suited to the characteristics of HSI data, but also avoids the possible limitations of manual design of neural networks when dealing with new classification tasks. However, the existing NAS-based HSIC methods have the following limitations: (1) the search space lacks efficient convolution operators that can fully extract discriminative spatial–spectral features, and (2) NAS based on traditional differentiable architecture search (DARTS) has performance collapse caused by unfair competition. To overcome these limitations, we proposed a neural architecture search method with receptive field spatial–spectral attention (RFSS-NAS), which is specifically designed to automatically search the optimal architecture for HSIC. Considering the core needs of the model in extracting more discriminative spatial–spectral features, we designed a novel and efficient attention search space. The core component of this innovative space is the receptive field spatial–spectral attention convolution operator, which is capable of precisely focusing on the critical information in the image, thus greatly enhancing the quality of feature extraction. Meanwhile, for the purpose of solving the unfair competition issue in the traditional differentiable architecture search (DARTS) strategy, we skillfully introduce the Noisy-DARTS strategy. The strategy ensures the fairness and efficiency of the search process and effectively avoids the risk of performance crash. In addition, to further improve the robustness of the model and ability to recognize difficult-to-classify samples, we proposed a fusion loss function by combining the advantages of the label smoothing loss and the polynomial expansion perspective loss function, which not only smooths the label distribution and reduces the risk of overfitting, but also effectively handles those difficult-to-classify samples, thus improving the overall classification accuracy. Experiments on three public datasets fully validate the superior performance of RFSS-NAS. [ABSTRACT FROM AUTHOR]

Geometrical models of the airways offer a comprehensive perspective on the complex interplay between lung structure and function. Originating from mathematical frameworks, these models have evolved to include detailed lung imagery, a crucial enhancement that aids in the early detection of morphological changes in the airways, which are often the first indicators of diseases. The accurate representation of airway geometry is crucial in research areas such as biomechanical modeling, acoustics, and particle deposition prediction. This review chronicles the evolution of these models, from their inception in the 1960s based on ideal mathematical constructs, to the introduction of advanced imaging techniques like computerized tomography (CT) and, to a lesser degree, magnetic resonance imaging (MRI). The advent of these techniques, coupled with the surge in data processing capabilities, has revolutionized the anatomical modeling of the bronchial tree. The limitations and challenges in both mathematical and image-based modeling are discussed, along with their applications. The foundation of image-based modeling is discussed, and recent segmentation strategies from CT and MRI scans and their clinical implications are also examined. By providing a chronological review of these models, this work offers insights into the evolution and potential future of airway geometry modeling, setting the stage for advancements in diagnosing and treating lung diseases. This review offers a novel perspective by highlighting how advancements in imaging techniques and data processing capabilities have significantly enhanced the accuracy and applicability of airway geometry models in both clinical and research settings. These advancements provide unique opportunities for developing patient-specific models. [ABSTRACT FROM AUTHOR]

This multicenter retrospective study evaluated the diagnostic performance of a deep learning (DL)-based application for detecting, classifying, and highlighting suspected aortic dissections (ADs) on chest and thoraco-abdominal CT angiography (CTA) scans. CTA scans from over 200 U.S. and European cities acquired on 52 scanner models from six manufacturers were retrospectively collected and processed by CINA-CHEST (AD) (Avicenna.AI, La Ciotat, France) device. The diagnostic performance of the device was compared with the ground truth established by the majority agreement of three U.S. board-certified radiologists. Furthermore, the DL algorithm's time to notification was evaluated to demonstrate clinical effectiveness. The study included 1303 CTAs (mean age 58.8 ± 16.4 years old, 46.7% male, 10.5% positive). The device demonstrated a sensitivity of 94.2% [95% CI: 88.8–97.5%] and a specificity of 97.3% [95% CI: 96.2–98.1%]. The application classified positive cases by the AD type with an accuracy of 99.5% [95% CI: 98.9–99.8%] for type A and 97.5 [95% CI: 96.4–98.3%] for type B. The application did not miss any type A cases. The device flagged 32 cases incorrectly, primarily due to acquisition artefacts and aortic pathologies mimicking AD. The mean time to process and notify of potential AD cases was 27.9 ± 8.7 s. This deep learning-based application demonstrated a strong performance in detecting and classifying aortic dissection cases, potentially enabling faster triage of these urgent cases in clinical settings. [ABSTRACT FROM AUTHOR]

The scalar auxiliary variable (SAV) approach of Shen et al. (2018), which presents a novel way to discretize a large class of gradient flows, has been extended and improved by many authors for general dissipative systems. In this work we consider a Cahn–Hilliard system with mass source that, for image processing and biological applications, may not admit a dissipative structure involving the Ginzburg–Landau energy. Hence, compared to previous works, the stability of SAV-discrete solutions for such systems is not immediate. We establish, with a bounded mass source, stability and convergence of time discrete solutions for a first-order relaxed SAV scheme in the sense of Jiang et al. (2022), and apply our ideas to Cahn–Hilliard systems with mass source appearing in diblock co-polymer phase separation, tumor growth, image inpainting, and segmentation. [ABSTRACT FROM AUTHOR]

In order to realize the accurate evaluation of queue posture and action, aiming at the problem that it is difficult to accurately measure the three-dimensional human posture characteristics such as kick height in the training scene, this paper proposed a queue three-dimensional posture feature detection method based on binocular information. The method is divided into two stages; the 2D pose estimation stage and binocular stereo matching stage. In order to improve the accuracy of 2D human pose detection, it designed a 2D pose estimation model based on the improved HRNet network. Firstly, it introduced spatial channel attention in the back-bone network to enhance feature extraction capabilities. The feature fusion layer used an adaptive spatial feature fusion module to fuse multi-scale features of the network. Secondly, it used the unbiased data processing method to encode and decode the heat map to reduce the statistical error of the data. Finally, it adopted a coarse-to-fine multi-stage supervision method during model training to improve the detection accuracy of key points. Based on the 2D pose estimation model, it used the standard correlation matching function to achieve binocular stereo matching, and then obtained the 3D human pose through coordinate transformation. The experimental results show that the improved pose estimation network has better accuracy, the accuracy of the COCO dataset reaches 77.1%, and the detection accuracy of the self-made queue training dataset reaches 86.3%, which are respectively 2.2% and 3.1% higher than the original network. In the kick height experiment of the three-dimensional human body posture, the average relative error measured by the proposed method is 2.5%, which fully verifies the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Cancer has been the leading cause of death among Japanese since 1981, and many people die from it every year worldwide. While various measures have been taken to reduce the mortality rate of cancer, circulating tumor cells (CTCs) in the blood have been attracting attention in recent years. In the past, CTCs were detected by visual inspection by a physician or by an expensive machine, but these methods required much effort by the physician and required only EpCAM‐expressing cells to be detected. In addition, detection by image processing has been used, but it has the problem that the area of interest is only a part of the area and there are many false positives. In this paper, we propose a two‐step classification method that focuses on the shape and surface of cells. In the proposed method, multiple shape and surface features are obtained for four types of cells in blood images: Clusters, CTCs, Normal Cells, and Vertical Cells. Based on the features, cells are classified using a two‐step Random Forest and their accuracy is evaluated. Furthermore, the effectiveness of the proposed method is demonstrated by comparing it with conventional methods. [ABSTRACT FROM AUTHOR]

The reproductive performance of sows can play a critical role in animal breeding, particularly in the efficiency and effectiveness of selection. However, manual recordings of piglet births and their survival rates cannot fully meet the large-scale production in recent years. The high precision is often required to capture more nuanced data, such as the intervals between births. The advanced technologies can be expected to enhance both the accuracy and efficiency of animal breeding programs. In this study, a lightweight network was developed to rapidly and accurately monitor the sow birthing in real time. Specifically, essential birthing metrics were engineered to analyze, such as the number of piglets born and the precise intervals between each birth. The lightweight network was tailored for the real-time monitoring of sow birthing activities. The critical birthing parameters were obtained to significantly enhance the efficiency and accuracy of breeding programs. Initially, the efficacy of different monitoring views—specifically, single versus double-column views—were evaluated on the accuracy of the improved model. A single-column view was significantly improved to accurately monitor the birthing events. The real-time decisionmaking and direct implications were obtained from the breeding outcomes. Advanced video processing techniques were incorporated, such as horizontal and vertical flipping. Some challenges were remained on the dynamic changes in the sow posture and varying camera perspectives during monitoring. Moreover, different lighting conditions were adapted to capture the inherent motion blur of active piglets during birth. Color jittering and Gaussian blur were then employed to significantly enhance the robustness of the model. The reliable performance was obtained under diverse operational conditions. Further advancements were achieved through a comparative analysis of classification networks. The results revealed that ResNet50 was greatly contributed to the recognition accuracy. MobileNetV3-S was performed the best with the compact model size and superior processing speed of 505.14 frames per second, indicating the optimal operational efficiency. Furthermore, MobileNetV3-S was refined to apply with the masked generative distillation—a sophisticated technique that was effectively enhanced the network's ability to capture and interpret essential birthing features. ResNet50 was utilized as the teacher model in the practical application, while MobileNetV3-S as the student model. The training was conducted using masked generative distillation followed by dependency graph pruning. The tests were carried out on a DELL OptiPlex microcomputer. An impressive detection speed of 83.10 frames per second was achieved with a test accuracy in a single-column field of view of 91.48%. Although there was a slight decrease in the accuracy of 0.98 percentage points, the detection speed was improved by 67.13 frames per second. This improved model was then deployed at the edge for testing. The better performance was achieved in the managed farrowing intervals with a detection error of just 0.31 seconds and the duration of piglet birth events with a mere 0.02-second error. Highly efficient and exceptionally precise real-time monitoring was obtained to promote the management practices of breeding activities in complex farm environments. In conclusion, the advanced computational techniques were integrated for the transformative potential to the monitoring of sow birthing. Real-time data was acquired to combine the image processing and machine learning. Some standards can be offered for the accuracy and efficiency in livestock management. The reproductive dynamics can greatly contribute to the sustainable and scientifically-informed animal husbandry. [ABSTRACT FROM AUTHOR]

Every year, more than two million Muslim pilgrims from all over the world visit Mecca to perform Hajj worship. The challenge of location identification in dense crowds is significant, leading to dangerous consequences such as injury or loss. Existing works for person localization remain challenged, especially in crowded places like Mecca during Hajj. In this work, we propose a novel location identification method using image pre-processing and different machine learning classifiers, with the creation of a new image dataset for hotspot locations in Mecca. Image pre-processing algorithms are applied to enhance the geographic information present in the images, and the obtained features are classified using CNN, ANN, and SVM classifiers. Extensive evaluations reveal that the proposed pre-processing algorithm with CNN achieves the best localization performance with an accuracy of 90%, followed by ANN with an accuracy of 84%, and SVM with an accuracy of 80.50%. Without pre-processing, the accuracies are significantly lower: 63% for CNN, 73% for ANN, and 71.50% for SVM. In addition, the proposed approach was compared with other deep learning models, VGG16, AlexNet and ResNet50 on our dataset achieving an accuracy of 61%, 65% and 62%, respectively. Results demonstrate the effectiveness of our proposed method in comparison with other deep transfer learning methods on a small dataset, offering promising solutions for crowded place navigation. [ABSTRACT FROM AUTHOR]

With the increasing complexity of digital systems, managing power dissipation and energy consumption in digital circuits, particularly in emerging embedded systems for artificial intelligence and signal processing applications, has become a challenging issue. The emerging paradigm of approximate computing offers the potential to reduce energy consumption and enhance speed by trading accuracy. This paper introduces several 4-bit approximate multipliers and outlines a systematic approach for constructing extended bit-length multipliers by leveraging lower bit-length counterparts. Our evaluations confirm that, in comparison with state-of-the-art approximate multipliers, the proposed multipliers demonstrate energy reduction of up to 50, 76, and 83% in 8-bit, 16-bit, and 32-bit multipliers, respectively. Additionally, the reduction in energy-delay product (EDP) reaches up to 86, 93, and 97%, correspondingly. The efficiency of the proposed approximate multipliers has been explored and confirmed in executing various image processing algorithms, a regression model developed for stock price prediction, and in executing quadrature amplitude demodulation. [ABSTRACT FROM AUTHOR]

Medical image segmentation through the use of deep learning is becoming a trend targeting to automate disease detection and provide effective treatment. Traditionally huge manual efforts are associated with medical image processing by medical staff. The wide use of neural networks driven by the progressive advancement in computing power and the availability of training data provides instrumental means to automate medical image processing. A polyp refers to an abnormal growth that can occur in various parts of the body. While the majority of polyps are noncancerous or benign, there are instances where certain types can develop into cancer. Detecting and segmenting polyps is highly valuable for identifying early signs and potentially enabling more effective treatment of colon cancer. In this paper, we introduce a novel method for segmenting polyp images. The proposed method utilizes convolutional neural networks (CNNs) and employs an enhanced attention mechanism. To cater to a more granular attention view, this paper enhances the Convolutional Block Attention Module by introducing the multi‐focal channel attention (MFCA) concept, which we call MFCA. In the proposed MFCA channel attention, focal attention spots allow us to consider scattered areas of interest more effectively. To evaluate the effectiveness of the proposed method, multiple experiments are conducted on five well‐known benchmark datasets for polyp image segmentation: Kvasir, CVC‐Clinic DB, CVC‐Colon DB, CVC‐T, and ETIS‐Larib. Various testing scenarios are examined, including the impact of two focal attention spots and four focal attention spots. The experimental results demonstrated that the proposed method achieved superior performance compared to previous state‐of‐the‐art techniques on two of the benchmark datasets, and ranked second on a third dataset. [ABSTRACT FROM AUTHOR]

Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumour that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumour is being intensively studied. Here, the automatic three‐dimensional segmentation of the GBM is achieved with its related subzones (active tumour, inner necrosis, and peripheral oedema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan–Vese active contours, and morphological erosion). After an automatic gap‐filling post processing step, these preliminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7%, and 66.4% for the entire region of interest, active tumour, oedema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results presented here evidence that it is possible to achieve the automatic segmentation of this kind of tumour by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post‐treatment response evaluation. [ABSTRACT FROM AUTHOR]

SUMMARY: The resolution of velocity models obtained by tomography varies due to multiple factors and variables, such as the inversion approach, ray coverage, data quality, etc. Combining velocity models with different resolutions can enable more accurate ground motion simulations. Toward this goal, we present a novel methodology to fuse multiresolution seismic velocity maps with probabilistic graphical models (PGMs). The PGMs provide segmentation results, corresponding to various velocity intervals, in seismic velocity models with different resolutions. Further, by considering physical information (such as ray path density), we introduce physics-informed probabilistic graphical models (PIPGMs). These models provide data-driven relations between subdomains with low (LR) and high (HR) resolutions. Transferring (segmented) distribution information from the HR regions enhances the details in the LR regions by solving a maximum likelihood problem with prior knowledge from HR models. When updating areas bordering HR and LR regions, a patch-scanning policy is adopted to consider local patterns and avoid sharp boundaries. To evaluate the efficacy of the proposed PGM fusion method, we tested the fusion approach on both a synthetic checkerboard model and a fault zone structure imaged from the 2019 Ridgecrest, CA, earthquake sequence. The Ridgecrest fault zone image consists of a shallow (top 1 km) high-resolution shear-wave velocity model obtained from ambient noise tomography, which is embedded into the coarser Statewide California Earthquake Center Community Velocity Model version S4.26-M01. The model efficacy is underscored by the deviation between observed and calculated traveltimes along the boundaries between HR and LR regions, 38 per cent less than obtained by conventional Gaussian interpolation. The proposed PGM fusion method can merge any gridded multiresolution velocity model, a valuable tool for computational seismology and ground motion estimation. [ABSTRACT FROM AUTHOR]

Generation of hidden attractor with complicated phase portrait in chaotic system with no equilibrium has presented a new research focus in the past decade. However, the existing approaches usually follow the rule that you reap what you sow, i.e., taking an no-equilibrium chaotic system as the seed. In this paper, a novel approach to the generation of no-equilibrium multi-fold hidden attractors is presented. The offset boosting and the operation of complex number are applied to several cases, including the seed chaotic systems with no equilibrium, with single unstable node, or with single stable node-focus. In specific, the offset boosting shifts the single non-zero equilibrium to the origin, then the operation of complex number rules out the equilibrium in the folded system and generates multi-fold trajectories. The highlight is that the proposed approach is not limited to the no-equilibrium seed system, but also applicable for different types of single-equilibrium seed systems, even the seed system with a single line of equilibrium. The detailed numerical simulations and experiments confirmed the feasibility of the proposed approach. Finally, an image encryption algorithm and its practical microcontroller-based implementation are presented to support the potential application. • Systematic approach for folding trajectory of chaotic system. • New multi-fold chaotic hidden attractors with no equilibrium. • New chaos-based encryption algorithm for image security. • Dynamic memory scheme for microcontroller implementation. [ABSTRACT FROM AUTHOR]