Search

The scanning electron microscope (SEM) recordings of dynamic nano-electromechanical systems (NEMS) are difficult to analyze due to the noise caused by low frame rate, insufficient resolution, and blurriness induced by applied electric potentials. Here, we develop an image processing platform enhanced by the physics of the underlying system to track the motion of buckling NEMS structures in the presence of high noise levels. The algorithm is composed of an image filter, two data filters, and a nonlinear regression model, which utilizes the expected form of the physical solution. The method was applied to the recordings of a NEMS beam about 150 nm wide, undergoing intra- and inter-well post-buckling states with a transition rate of approximately 0.5 Hz. The algorithm can track the dynamical motion of the NEMS and capture the dependency of deflection amplitude on the compressive force on the beam. With the help of the proposed algorithm, the transition from inter-well to intra-well motion is clearly resolved for buckling NEMS imaged under SEM. [ABSTRACT FROM AUTHOR]

Photoluminescence imaging of field-installed photovoltaic modules has the potential to be a high throughput on-site inspection technique. A contribution to this development is a noninvasive photoluminescence imaging method that has been proposed recently. It is based on acquiring images during a progressing current–voltage curve sweep, resulting in a detection of a continuously changing photoluminescence signal. From this follows the necessity to employ an alternative algorithm based on the Pearson correlation coefficient, which will contribute to efficient, unsupervised image processing and, thus, easier (in real-time) implementation. The new algorithm separates photoluminescence from the reflected sunlight, similar to the conventional subtraction algorithm. However, it is robust to varying solar irradiance and can process the photoluminescence signal emitted from multiple asynchronized strings. We predict that it will enable unsupervised real-time surveillance and detection of functional anomalies at a low computational cost. It is also more sensitive at segmenting ground-reflected photoluminescence. [ABSTRACT FROM AUTHOR]

Tensile testing (aka tension testing) is a widely employed mechanical testing technique for analyzing materials' properties and behavior under applied stress. Tensile testing plays a pivotal role in helping engineers to make informed decision about material selection and usage. Despite its importance, there is a limited numbers of studies that explored the potential of AI techniques for real time monitoring and material behavior prediction in tensile testing. To this end, this work presents a deep learning model designed to predict the material's condition throughout tensile testing and provide an early warning prior to fracture. By leveraging a comprehensive dataset of tension test video samples, the proposed model utilizes both convolution and recurrent neural networks to extract pertinent spatial and temporal visual features, thereby predicting the frames at which material deformation and fracture occur. The evaluation results of our research showed that the proposed model achieved a predictive ability with an F1-score of 97%, on average. The implications of our research are significant for industries and researchers in the field of materials science and engineering. By accurately predicting material status, our model enables autonomous, real time analysis of material behavior during tensile testing, leading to better time and cost efficiency in various applications. [ABSTRACT FROM AUTHOR]

We introduce a novel technique to mitigate the adverse effects of atmospheric turbulence on astronomical imaging. Utilizing a video-to-image neural network trained on simulated data, our method processes a sliding sequence of short-exposure (∼0.2 s) stellar field images to reconstruct an image devoid of both turbulence and noise. We demonstrate the method with simulated and observed stellar fields, and show that the brief exposure sequence allows the network to accurately associate speckles to their originating stars and effectively disentangle light from adjacent sources across a range of seeing conditions, all while preserving flux to a lower signal-to-noise ratio than an average stack. This approach results in a marked improvement in angular resolution without compromising the astrometric stability of the final image. [ABSTRACT FROM AUTHOR]

Finding patches is a crucial step in a pavement performance survey. The study develops a machine learning and image processing algorithm-established automatic method for identifying asphalt pavement patches. The GrayLevel Co-Occurrence Matrix and image texture-based features derived from color channel statistics are used as input parameters to describe the condition of the pavement. For feature extraction, image processing methods like the projective integral of images, steerable filters, and an improved image thresholding method were used. Support Vector Machine is employed for categorizing the differentiating patched regions from non-patch ones. The suggested combination of image texture analytical methods has been trained using an IA data set created from 400 image samples. The feature set, which combines the characteristics of cracked objects with those generated from the projective integral, can produce the desired result. To make the model's execution simpler, a patch recognition program was created and implemented in MATLAB. As a result, the recently created method has the potential to be an instrument for traffic management organizations through the assessment of pavement performance. The results of the experiments indicate that the newly developed method may achieve excellent accuracy prediction results with a classifier performance rate of about 96%. Such a method could enable transportation authorities to assess the state of asphalt pavement. [ABSTRACT FROM AUTHOR]

Multiplicative noise removal is a challenging image processing problem. In this paper, we study a fractional-order nonlinear cross-diffusion system to denoise images corrupted by multiplicative Gamma noise. The system is coupled by two nonlinear, partial differential equations and gray level information, fractional derivative operator is considered in diffusion process to remove high level noise effectively while preserve structure details for texture images and SAR images. We prove the existence of weak solutions and other theoretical properties of the fractional-order cross-diffusion system under some hypotheses. In the numerical aspect, the model is implemented by virtue of the discrete fractional Fourier transform in the frequency domain. Experimental results show that the new system has a good compromise between multiplicative noise removal and structure preservation when compared to other well-known denoising methods. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Focusing on the complicated pathological features, such as blurred boundaries, severe scale differences between symptoms, and background noise interference, we aim to enhance the reliability of multiple lesions joint segmentation from medical images.Propose a novel reliable multi‐scale wavelet‐enhanced transformer network, which can provide accurate segmentation results with reliability assessment.Focusing on enhancing the model's capability to capture intricate pathological features in medical images, this work introduces a novel segmentation backbone. The backbone integrates a wavelet‐enhanced feature extractor network and incorporates a multi‐scale transformer module developed within the scope of this work. Simultaneously, to enhance the reliability of segmentation outcomes, a novel uncertainty segmentation head is proposed. This segmentation head is rooted in the SL, contributing to the generation of final segmentation results along with an associated overall uncertainty evaluation score map.Comprehensive experiments are conducted on the public database of AI‐Challenge 2018 for retinal edema lesions segmentation and the segmentation of Thoracic Organs at Risk in CT images. The experimental results highlight the superior segmentation accuracy and heightened reliability achieved by the proposed method in comparison to other state‐of‐the‐art segmentation approaches.Unlike previous segmentation methods, the proposed approach can produce reliable segmentation results with an estimated uncertainty and higher accuracy, enhancing the overall reliability of the model. The code will be release on https://github.com/LooKing9218/ReMultiSeg. [ABSTRACT FROM AUTHOR]

Concerns regarding microplastic (MP) contamination in aquatic ecosystems and its impact on seafood require a better understanding of human dietary MP exposure including extensive monitoring. While conventional techniques for MP analysis like infrared or Raman microspectroscopy provide detailed particle information, they are limited by low sample throughput, particularly when dealing with high particle numbers in seafood due to matrix-related residues. Consequently, more rapid techniques need to be developed to meet the requirements of large-scale monitoring. This study focused on semi-automated fluorescence imaging analysis after Nile red staining for rapid MP screening in seafood. By implementing RGB-based fluorescence threshold values, the need for high operator expertise to prevent misclassification was addressed. Food-relevant MP was identified with over 95% probability and differentiated from natural polymers with a 1% error rate. Comparison with laser direct infrared imaging (LDIR), a state-of-the-art method for rapid MP analysis, showed similar particle counts, indicating plausible results. However, highly variable recovery rates attributed to inhomogeneous particle spiking experiments highlight the need for future development of certified reference material including sample preparation. The proposed method demonstrated suitability of high throughput analysis for seafood samples, requiring 0.02–0.06 h/cm2 filter surface compared to 4.5–14.7 h/cm with LDIR analysis. Overall, the method holds promise as a screening tool for more accurate yet resource-intensive MP analysis methods such as spectroscopic or thermoanalytical techniques. [ABSTRACT FROM AUTHOR]

This study presents a novel photodiode technology with augmented optoelectronic capabilities through the incorporation of quantum dots (QDs). The photodiode, composed of Indium Gallium Zinc Oxide‐Tellurium (IGZO‐Te), is engineered for enhanced light sensitivity and tailored optoelectronic interactions. The primary application of this advanced photodiode lies in the domain of artificial intelligence and machine learning, where it plays a pivotal role in simulating synaptic connections for image processing tasks. Due to the exceptional optical and electrical properties of the IGZO‐Te‐QDs active material combination, the photodiode demonstrates consistent and dependable optical synaptic functions linked to learning. This is achieved through conduction modulation and time duration modulation of light stimulus. In addition, the opto‐synaptic functionalities such as short‐term and long‐term memory has also been successfully demonstrated not only on single device but also on 6 × 6 photodiodes array device. These findings underscore the significant potential of the hybrid structure of IGZO‐Te with QDs in optical artificial neuromorphic chips. [ABSTRACT FROM AUTHOR]

ObjectiveAimMethodResultsConclusionThyroid carcinoma ranks as the 9th most prevalent global cancer, accounting for 586,202 cases and 43,636 deaths in 2020. Computerized image analysis, utilizing artificial intelligence algorithms, emerges as a potential tool for tumor evaluation.This study aims to assess and compare chromatin textural characteristics and nuclear dimensions in follicular neoplasms through gray-level co-occurrence matrix (GLCM), fractal, and morphometric analysis.A retrospective cross-sectional study involving 115 thyroid malignancies, specifically 49 papillary thyroid carcinomas with follicular morphology, was conducted from July 2021 to July 2023. Ethical approval was obtained, and histopathological examination, along with image analysis, was performed using ImageJ software.A statistically significant difference was observed in contrast (2.426 (1.774–3.412) vs 2.664 (1.963–3.610), p = .002), correlation (1.202 (1.071–1.298) vs 0.892 (0.833–0.946), p = .01), and ASM (0.071 (0.090–0.131) vs 0.044 (0.019–0.102), p = .036) between NIFTP and IFVPTC. However, morphometric parameters did not yield statistically significant differences among histological variantsComputerized image analysis, though promising in subtype discrimination, requires further refinement and integration with traditional diagnostic parameters. The study suggests potential applications in scenarios where conventional histopathological assessment faces limitations due to limited tissue availability. Despite limitations such as a small sample size and a retrospective design, the findings contribute to understanding thyroid carcinoma characteristics and underscore the need for comprehensive evaluations integrating various diagnostic modalities. [ABSTRACT FROM AUTHOR]

The proliferation of smart conurbations entails an efficient system design for managing all the crowds in public places. Multitude controlling procedures are carried out for controlling compact areas where more number of peoples is present at several groups. Therefore for controlling purpose the proposed method aims to design a pictorial representation using Internet of Things (IoT). The process is carried out by taking images and then organizing it using switching techniques in the presence of square boxes where entire populace is identified on real time experimentations. For processing and controlling the occurrence a separate architecture is designed with analytical equivalences where all data set is stored in cloud platform. Further the incorporation of system model is carried out using Switching Based Algorithm (SBA) which adds more number of columns even for high population cases. In order to verify the effectiveness of proposed model five scenarios are considered with performance evaluation metrics for SBA and all the test results provides best optimal results. Moreover the projected model is improved with an average percentage of 83 as compared to existing models. [ABSTRACT FROM AUTHOR]

Crop yield predictions are important for crop monitoring and agronomic management. The traditional methods for yield predictions are complicated and resource consuming. With the availability of affordable handheld imaging and computing devices, the image processing-based yield prediction methods are gaining popularity. In this work, RGB images of rice panicles are captured using DSLR camera with simple background and processed to determine the panicle area in terms of number of pixels. A machine learning-based model is developed to make predictions for rice yield. The model is trained to make predictions on unseen data. Various machine learning-based regression algorithms including decision tree, random forest, support vector machine, and convolution neural network are tested. The experiments are performed on a publically available dataset from China as well as on a self-acquired dataset in India. The results have shown that image processing and machine learning-based methods can make yield predictions satisfactorily as evident from the coefficient of determination ( R 2 ) that ranges 0.80–0.97 for different cultivars. The prediction error is determined in terms of root mean square error (RMSE) and mean absolute error (MAE). RMSE for different methods lies between 0.14 and 0.40, whereas MAE varies from 0.11 to 0.30. Among the tested algorithms, linear regression achieved the best precision with R 2 = 0.97, RMSE = 0.14, and MAE = 0.11. [ABSTRACT FROM AUTHOR]

STUDY QUESTION Can generative artificial intelligence (AI) models produce high-fidelity images of human blastocysts? SUMMARY ANSWER Generative AI models exhibit the capability to generate high-fidelity human blastocyst images, thereby providing substantial training datasets crucial for the development of robust AI models. WHAT IS KNOWN ALREADY The integration of AI into IVF procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative adversarial networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images. STUDY DESIGN, SIZE, DURATION Blastocyst images were included as training data from a public dataset of time-lapse microscopy (TLM) videos (n = 136). A style-based GAN was fine-tuned as the generative model. PARTICIPANTS/MATERIALS, SETTING, METHODS We curated a total of 972 blastocyst images as training data, where frames were captured within the time window of 110–120 h post-insemination at 1-h intervals from TLM videos. We configured the style-based GAN model with data augmentation (AUG) and pretrained weights (Pretrained-T: with translation equivariance; Pretrained-R: with translation and rotation equivariance) to compare their optimization on image synthesis. We then applied quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance by measuring the intelligence behavior of the model through the visual Turing test. To this end, 60 individuals with diverse backgrounds and expertise in clinical embryology and IVF evaluated the quality of synthetic embryo images. MAIN RESULTS AND THE ROLE OF CHANCE During the training process, we observed consistent improvement of image quality that was measured by FID and KID scores. Pretrained and AUG + Pretrained initiated with remarkably lower FID and KID values compared to both Baseline and AUG + Baseline models. Following 5000 training iterations, the AUG + Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004, respectively. Subsequently, we carried out the visual Turing test, such that IVF embryologists, IVF laboratory technicians, and non-experts evaluated the synthetic blastocyst-stage embryo images and obtained similar performance in specificity with marginal differences in accuracy and sensitivity. LIMITATIONS, REASONS FOR CAUTION In this study, we primarily focused the training data on blastocyst images as IVF embryos are primarily assessed in blastocyst stage. However, generation of an array of images in different preimplantation stages offers further insights into the development of preimplantation embryos and IVF success. In addition, we resized training images to a resolution of 256 × 256 pixels to moderate the computational costs of training the style-based GAN models. Further research is needed to involve a more extensive and diverse dataset from the formation of the zygote to the blastocyst stage, e.g. video generation, and the use of improved image resolution to facilitate the development of comprehensive AI algorithms and to produce higher-quality images. WIDER IMPLICATIONS OF THE FINDINGS Generative AI models hold promising potential in generating high-fidelity human blastocyst images, which allows the development of robust AI models as it can provide sufficient training datasets while safeguarding patient data privacy. Additionally, this may help to produce sufficient embryo imaging training data with different (rare) abnormal features, such as embryonic arrest, tripolar cell division to avoid class imbalances and reach to even datasets. Thus, generative models may offer a compelling opportunity to transform embryo selection procedures and substantially enhance IVF outcomes. STUDY FUNDING/COMPETING INTEREST(S) This study was supported by a Horizon 2020 innovation grant (ERIN, grant no. EU952516) and a Horizon Europe grant (NESTOR, grant no. 101120075) of the European Commission to A.S. and M.Z.E. the Estonian Research Council (grant no. PRG1076) to A.S. and the EVA (Erfelijkheid Voortplanting & Aanleg) specialty program (grant no. KP111513) of Maastricht University Medical Centre (MUMC+) to M.Z.E. TRIAL REGISTRATION NUMBER Not applicable. [ABSTRACT FROM AUTHOR]

Segmentation is crucial in diagnosing retinal diseases by accurately identifiying retinal vessels. This paper addresses the complexity of segmenting retinal vessels, highlighting the need for precise analysis of blood vessel structures. Despite the progress made by convolutional neural networsks (CNNs) in image segmentation, their limitations in capturing the global structure of retinal vsessels and maintaining segmentation continuity present challenges. To tackle these issues, our proposed network integrates graph convolutional networks (GCNs) and attention mechansims. This allows the model to consider pixel relationships and learn vessel graphical structures, significantly improving segmentation accuracy. Additionally, the attentional feature fusion module, including pixel‐wise and channel‐wise attention mechansims within the U‐Net architecture, refines the model's focus on relevant features. This paper emphasizes the importance of continuty preservation, ensuring an accurate representation of pixel‐level information and structural details during sefmentation. Therefore, our method performs as an effective solution to overcome challenges in retinal vessel segmentation. The proposed method outperformed the state‐of‐the‐art approaches on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (Structed Analysis of the Retina) datasets with accuracies of 0.12% and 0.14%, respecttively. Importantly, our proposed approach excelled in delineating slender and diminutive blood vessels, crucial for diagnosing vascular‐related diseases. Implementation is accessible on https://github.com/CVLab‐SHUT/VGA‐Net. [ABSTRACT FROM AUTHOR]

In recent years, low‐light image enhancement has become increasingly active. However, in underground mine environments, acquiring high‐quality images is still challenging due to low light, low contrast, and occlusion. To address this problem, this study proposes a low‐light image enhancement method for underground mine based on generative adversarial networks (UM‐GAN), which aims to take full advantage of the ability of GAN to achieve the restoration of details, the reduction of noise, and the improvement of overall image quality. The model proposed in this paper is divided into three main parts. Initially, a generator network adopting an encoder–decoder structure is developed. Subsequently, a novel strategy is introduced to merge information by utilizing inverted greyscale images and low‐light images as inputs. Further image quality enhancement is achieved by incorporating a noise reduction module employing the diffusion model. To ascertain the efficacy of the UM‐GAN method, evaluations are conducted on diverse real‐world and synthetic datasets, juxtaposing the approach against superior methods. Through qualitative and quantitative comparative experiments, the method showcases noteworthy advancements through qualitative and quantitative comparative experiments, substantiating its effectiveness. This research provides new ideas and methods for overcoming image quality problems in underground mine environments and contributes to the development of underground mine image processing. [ABSTRACT FROM AUTHOR]

The surface quality of steel strip is a critical indicator of the quality of hot‐rolled strip, so accurate inspection of its surface is essential. However, the complex texture of steel strip surface defects makes the detection challenging. Here, a multi‐scale feature fusion and attention based YOLOv5 (MFFA‐YOLOv5) model is proposed. Specifically, the bottom layer features are up‐sampled and fused not only with the middle layer features, but also with the top layer features, so that the model better captures the surface texture information of the steel strip. Secondly, an improved attention mechanism module is introduced to deal with the global and local information of the steel strip surface by introducing down‐sampling and up‐sampling paths based on Convolutional Block Attention Module (CBAM). Meanwhile, a self‐attention mechanism path is added to improve the capability of feature representation. Experimental results on the NEU‐DET dataset show that the MFFA‐YOLOv5 model significantly outperforms other state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Slug flow processes draw much attention in chemical and pharmaceutical manufacturing thanks to their ability to eliminate downtime costs and batch‐to‐batch variation. Using in‐line video can monitor the current process status and improve the stability of the slug flow. However, there are no effective image processing methods aiming at such videos from chemical experiments due to limited training sample size and the variety of experimental settings. The paper proposes a training‐free method to automatically detect and measure the slugs from in‐line videos. Multiple image features are fused to identify the slug shapes under various lighting conditions, a six‐point model is fitted to achieve better volume estimation, and a consistency score is estimated to quantify the detection uncertainty. The proposed algorithm achieves similar results to manual labeling for various types of slug flow processes, improving the accuracy of slug column estimation by a large margin compared to the existing automatic methods. Finally, using it to monitor the slug flow process's stability and the change of the slug volume in an injection point are demonstrated. The method not only shows that handcrafted image features have the capability for detection and segmentation from chemical experiment images but also paves the road for a training‐based algorithm for the task. [ABSTRACT FROM AUTHOR]

The demand for less complex and more accurate architectures has always been a priority since the broad usage of computer vision in everyday life, like auto‐drive cars, portable applications, augmented reality systems, medical image analysis etc. There are a lot of methods that have been developed to improve the accuracy and complexity of object detection, like the generations of R‐CNNs and YOLOs. However, these methods are not the most efficient architectures, and there is always room to improve. In this study, the 5th version of YOLO is employed and the improved architecture, Inception‐YOLO, is presented. The model significantly outperforms the SOTA YOLO family. Specifically, the improvements can be summarised as follows: impressive improvement of floating point operations (FLOPs) and number of parameters, as well as improvement in accuracy compared to the models with fewer FLOPs. All our presented approaches, like the optimized inception module, proposed structures for CSP and SPPF, and the improved loss function used in this research, work together to incrementally improve detection results, accuracy, demanded memory, and FLOPs simultaneously. For a glimpse of performance, the Inception‐YOLO‐S model hits 38.7% AP with 5.9M parameters and 11.5 BFLOPs and outperforms YOLOv5‐S with 37.4% AP, 7.2M parameters, and 16.5 BFLOPs. [ABSTRACT FROM AUTHOR]

Low‐light image enhancement is a longstanding challenge in low‐level vision, as images captured in low‐light conditions often suffer from significant aesthetic quality flaws. Recent methods based on deep neural networks have made impressive progress in this area. In contrast to mainstream convolutional neural network (CNN)‐based methods, an effective solution inspired by the transformer, which has shown impressive performance in various tasks, is proposed. This solution is centred around two key components. The first is an image synthesis pipeline, and the second is a powerful transformer‐based pre‐trained model, known as the low‐light image enhancement transformer (LIET). The image synthesis pipeline includes illumination simulation and realistic noise simulation, enabling the generation of more life‐like low‐light images to overcome the issue of data scarcity. LIET combines streamlined CNN‐based encoder‐decoders with a transformer body, efficiently extracting global and local contextual features at a relatively low computational cost. The extensive experiments show that this approach is highly competitive with current state‐of‐the‐art methods. The codes have been released and are available at LIET. [ABSTRACT FROM AUTHOR]

In the realm of video salient object detection (VSOD), the majority of research has traditionally been centered on third‐person perspective videos. However, this focus overlooks the unique requirements of certain first‐person tasks, such as autonomous driving or robot vision. To bridge this gap, a novel dataset and a camera‐based VSOD model, CaMSD, specifically designed for egocentric videos, is introduced. First, the SalEgo dataset, comprising 17,400 fully annotated frames for video salient object detection, is presented. Second, a computational model that incorporates a camera movement module is proposed, designed to emulate the patterns observed when humans view videos. Additionally, to achieve precise segmentation of a single salient object during switches between salient objects, as opposed to simultaneously segmenting two objects, a saliency enhancement module based on the Squeeze and Excitation Block is incorporated. Experimental results show that the approach outperforms other state‐of‐the‐art methods in egocentric video salient object detection tasks. Dataset and codes can be found at https://github.com/hzhang1999/SalEgo. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Computer Vision, discussing the topic of advanced image restoration and enhancement. The editorial highlights the challenges faced in this field, such as the complexity of degradation models for real-world low-quality images and the difficulty of acquiring paired data. It also introduces a special issue of the journal that includes five accepted papers, which focus on video reconstruction and image super-resolution. The editorial concludes by providing brief summaries of each accepted paper. The guest editors of the special issue are also mentioned, along with their research interests and affiliations. [Extracted from the article]

Perception systems in autonomous vehicles need to accurately detect and classify objects within their surrounding environments. Numerous types of sensors are deployed on these vehicles, and the combination of such multimodal data streams can significantly boost performance. The authors introduce a novel sensor fusion framework using deep convolutional neural networks. The framework employs both camera and LiDAR sensors in a multimodal, multiview configuration. The authors leverage both data types by introducing two new innovative fusion mechanisms: element‐wise multiplication and multimodal factorised bilinear pooling. The methods improve the bird's eye view moderate average precision score by +4.97% and +8.35% on the KITTI dataset when compared to traditional fusion operators like element‐wise addition and feature map concatenation. An in‐depth analysis of key design choices impacting performance, such as data augmentation, multi‐task learning, and convolutional architecture design is offered. The study aims to pave the way for the development of more robust multimodal machine vision systems. The authors conclude the paper with qualitative results, discussing both successful and problematic cases, along with potential ways to mitigate the latter. [ABSTRACT FROM AUTHOR]

Recent advances in deep convolutional neural networks have shown improved performance in face super‐resolution through joint training with other tasks such as face analysis and landmark prediction. However, these methods have certain limitations. One major limitation is the requirement for manual marking information on the dataset for multi‐task joint learning. This additional marking process increases the computational cost of the network model. Additionally, since prior information is often estimated from low‐quality faces, the obtained guidance information tends to be inaccurate. To address these challenges, a novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding. Specifically, the proposed GLFEU is composed of an attention branch and a Transformer branch, to simultaneously restore global facial structure and local texture details. Additionally, a Multi‐Stage Feature Fusion Module is incorporated to fuse features from different network stages, further improving the quality of the restored face images. Compared with previous methods, DCTNet improves Peak Signal‐to‐Noise Ratio by 0.23 and 0.19 dB on the CelebA and Helen datasets, respectively. Experimental results demonstrate that the designed DCTNet offers a simple yet powerful solution to recover detailed facial structures from low‐quality images. [ABSTRACT FROM AUTHOR]

In recent years, many methods for image super‐resolution (SR) have relied on pairs of low‐resolution (LR) and high‐resolution (HR) images for training, where the degradation process is predefined by bicubic downsampling. While such approaches perform well in standard benchmark tests, they often fail to accurately replicate the complexity of real‐world image degradation. To address this challenge, researchers have proposed the use of unpaired image training to implicitly model the degradation process. However, there is a significant domain gap between the real‐world LR and the synthetic LR images from HR, which severely degrades the SR performance. A novel unsupervised image‐blind super‐resolution method that exploits degradation feature‐based learning for real‐image super‐resolution reconstruction (RDFL) is proposed. Their approach learns the degradation process from HR to LR using a generative adversarial network (GAN) and constrains the data distribution of the synthetic LR with real degraded images. The authors then encode the degraded features into a Transformer‐based SR network for image super‐resolution reconstruction through degradation representation learning. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness and superiority of the RDFL method, which achieves visually pleasing reconstruction results. [ABSTRACT FROM AUTHOR]

Mobile devices and handheld systems, such as the smartphones and tablets universally extended, are becoming increasingly powerful. Their basic hardware configuration is usually state-of-the-art heterogeneous architectures consisting of multi-core processors and some kind of accelerator such as GPUs or DSPs. Specific code adapted to the architecture is mandatory if high-performance computation is required and low-level libraries and parallelism are needed, which constitutes an important barrier for the usual developer in such devices. In this context, we propose the FancyJCL framework. It provides a high-level abstraction layer that hides implementation details and allows to develop parallel programs for mobile devices. The target platform for FancyJCL is mainly Android and Java developers due to their high market penetration. A very simple, seemingly sequential encoding results in parallel efficient OpenCL code. FancyJCL is itself based on the Fancier framework, which enables optimal memory management across memory spaces on unified memory systems. Benchmarks of FancyJCL code developed for a wide range of image processing algorithms show good performance with low development effort. [ABSTRACT FROM AUTHOR]

Conventional image processing and machine learning based on handcrafted features struggle to meet the real time and high-accuracy requirements for industrial defect detection in complex, sensitive, and dynamic environments. To address this issue, this paper proposes AENet, a novel real-time defect detection network based on an encoder-decoder model, which achieves high detection accuracy and efficiency while demonstrating excellent convergence and generalization. Firstly, a spatial channel attention module in the encoding network is designed to exploit both spatial attention and channel attention using a multi-head 3D self-attention mechanism. This improves parallelism and detection efficiency. Secondly, the decoding network of AENet incorporates the cross-level attention fusion module, which fuses input features from different layers. Combined with multi-level upsampling design, the decoder enhances the representation of defect details. Furthermore, we insert a simplified aggregator into the encoder-decoder network to extract feature information at different scales with low computational cost. This aggregation process aids in training and inference on industrial defect datasets by incorporating contextual information. Extensive experimental results demonstrate that AENet outperforms other segmentation models in accomplishing defect recognition and segmentation in challenging optical environments. It exhibits a faster convergence than other networks and a balance between accuracy and speed. It achieves a recognition accuracy of over 96% for almost all types of defects in the actual industrial environment on the NVIDIA Tesla V100 GPU. [ABSTRACT FROM AUTHOR]

While the fabric of soil can significantly influence its behaviour, the effect of varying fabric parameters on the subgrade shear response is still not well understood. This study creates soil specimens with different fabrics which are then captured through X-ray microscopic-computed tomography scanning and quantified by image processing techniques. A comprehensive laboratory investigation is conducted to understand how the soil fabric affects its monotonic and cyclic shear behaviour. The results indicate that the consolidation method creates a more homogeneous fabric with mainly small-to-medium interconnected pores, whereas the compaction technique creates significantly large and mostly inter-aggregate pores with lower connectivity. In this regard, the consolidated specimens exhibit an elastic-perfectly plastic behaviour, while the compacted specimens show strain-hardening transformation during isotropic monotonic shearing. Under anisotropic conditions, the compacted specimens exhibit a greater strain softening response and excess pore pressure than the consolidated specimens because they have a weaker fabric. Furthermore, the compacted specimens show a smaller threshold strain at a lower critical number of cycles due to the collapse of large pores. These current findings prove the decisive role that soil fabric plays in determining the shear response and failure of subgrade soils. [ABSTRACT FROM AUTHOR]

Rock strength parameters such as uniaxial compressive strength and modulus of elasticity are crucial parameters in designing rock engineering structures. Owing to the importance of the aforementioned parameters, in this paper, image processing technique is coupled with artificial neural network (ANN) method for assessing the uniaxial compressive strength and modulus of elasticity of sandstones. For this reason, 102 core sandstone samples were prepared. Subsequently petrographic analyses and imaging operation for 102 images were performed. Principal component analysis was then conducted for feature reduction purposes. At last, an ANN model, which received its input data from image processing technique, was constructed for assessing the UCS and E of sandstone samples. Overall, the best performance of the network was obtained when 10 hidden nodes were used. The correlation coefficient (R) values of 0.9722 and 0.97062 for UCS and E, respectively, suggest the feasibility of the proposed model. [ABSTRACT FROM AUTHOR]

Apple-picking robot can promote the development of smart agriculture, and accurate object recognition in complex natural environments using deep learning algorithms is critical. However, research has shown that changes in illumination and object occlusion remain significant challenges for recognition. In order to improve the accuracy of apple apple-picking robot’s identification and positioning of apples in natural environment, a method using YOLOv5 (You Only Look Once, YOLO) combined with fast-guided filter is proposed. By introducing a fast-guided filtering module, the ability to extract image features is improved, and the problem of inaccurate occlusion targets and edge detection is solved; K-means clustering algorithm is introduced in improving YOLOv5, which can realize automatic adjustment of image size and step size; BiFPN structure is introduced in Neck network to add weighted feature fusion to highlight the detailed features. The results show that the algorithm proposed in this paper can well remove noise information such as occlusion edge blurring in apple images in a natural light environment. In the real orchard environment, the apple recognition accuracy rate reached 97.8%, the recall rate was 97.3% and the recognition rate was about 26.84fps. The results show that this research based on YOLOv5 and fast-guided filtering can realize fast and accurate identification of apple fruits in natural environment, and meet the practical application requirements of real-time target detection. [ABSTRACT FROM AUTHOR]

A stochastic network simulation is verified when its distribution of outputs is aligned with the ground truth, while tolerating deviations due to variability in real-world measurements and the randomness of a stochastic simulation. However, comparing distributions may yield false positives, as erroneous simulations may have the expected distribution yet present aberrations in low-level patterns. For instance, the number of sick individuals may present the right trend over time, but the wrong individuals were infected. We previously proposed an approach that transforms simulation traces into images verified by machine learning algorithms that account for low-level patterns. We demonstrated the viability of this approach when many simulation traces are compared with a large ground truth data set. However, ground truth data are often limited. For example, a publication may include few images of their simulation as illustrations; hence, teams that independently re-implement the model can only compare low-level patterns with few cases. In this paper, we examine whether our approach can be utilized with very small data sets (e.g., 5–10 images), as provided in publications. Depending on the network simulation model (e.g., rumor spread, cascading failure, and disease spread), we show that results obtained with little data can even surpass results obtained with moderate amounts of data at the cost of variability. Although a good accuracy is obtained in detecting several forms of errors, this paper is only a first step in the use of this technique for verification; hence, future works should assess the applicability of our approach to other types of network simulations. [ABSTRACT FROM AUTHOR]

With the increasing popularity of machine learning (ML) in image processing, privacy concerns have emerged as a significant issue in deploying and using ML services. However, current privacy protection approaches often require computationally expensive training from scratch or extensive fine-tuning of models, posing significant barriers to the development of privacy-conscious models, particularly for smaller organizations seeking to comply with data privacy laws. In this paper, we address the privacy challenges in computer vision by investigating the effectiveness of two recent fine-tuning methods, Model Reprogramming and Low-Rank Adaptation. We adapt these techniques to provide attribute protection for pre-trained models, minimizing computational overhead and training time. Specifically, we modify the models to produce privacy-preserving latent representations of images that cannot be used to identify unintended attributes. We integrate these methods into an adversarial min–max framework, allowing us to conceal sensitive information from feature outputs without extensive modifications to the pre-trained model, but rather focusing on a small set of new parameters. We demonstrate the effectiveness of our methods by conducting experiments on the CelebA dataset, achieving state-of-the-art performance while significantly reducing computational complexity and cost. Our research provides a valuable contribution to the field of computer vision and privacy, offering practical solutions to enhance the privacy of machine learning services without compromising efficiency. [ABSTRACT FROM AUTHOR]

Savoring is a positive emotion up‐regulation technique that can increase electrocortical and self‐reported valence and arousal to positive and neutral pictures, with effects persisting to increase response to the same stimuli when encountered later. Outside of the lab, emotion regulation techniques that persist to affect not just encounters with the same stimuli but also encounters with similar, but previously unencountered stimuli should save individuals time and effort. Here, we used event‐related potentials and picture ratings to test whether savoring would generalize to similar, but previously unseen positive pictures. To this end, 89 participants (56 female; M age = 18.96 years, SD = 1.87) were asked to savor positive pictures from one category (e.g., happy people) and to view positive pictures from another category (e.g., cute animals), as well as to view neutral pictures (e.g., plants). In a subsequent passive picture viewing task, participants viewed novel pictures from all three categories (i.e., happy people, cute animals, plants). In the first task, savoring was effective for pictures of animals throughout picture presentation, but only for pictures of people during the later part of picture presentation. In the second task, savoring generalized to novel pictures of animals, though this was only evident in the early portion of picture processing (and for self‐reported ratings). Therefore, savoring holds promise as a useful technique for increasing positive emotion in everyday life, though more work is needed to understand whether effects may vary depending on different types of picture content. We tested whether savoring, a technique for increasing positive emotion, would generalize to novel, similar stimuli, thereby saving individuals time and effort. Participants performed a savor and view task, before viewing similar pictures in a passive view task. Results showed that pictures resembling those that had previously been savored elicited increased late positive potentials and more emotional ratings than pictures resembling those that had been viewed. Nonetheless, effects were specific to certain picture content. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for 3D data cube denoising, where the 3D data cube is corrupted by noise with spatially varying noise levels. We perform 3D dual tree complex wavelet transform (DTCWT) to the 3D data cube, and then conduct wavelet-based thresholding based on three scales of dependency in wavelet coefficients. Instead of using the global noise level, we estimate the noise levels locally, which improve the denoising results substantially. We conduct inverse DTCWT to obtain the noise reduced data cubes. Experiments demonstrate that our proposed method outperforms block matching and 3D filtering, video block matching and 3D filtering, 2D bivariate shrinkage, and 3D bivariate shrinkage significantly for noise reduction of 3D data cubes. [ABSTRACT FROM AUTHOR]

Decomposing an image into meaningful components is an effective way for image processing. Making full use of cartoon features and texture features with deep neural networks may further achieve the stable noise cancellation performance for low-dose computed tomography (LDCT) denoising. However, the performance of conventional deep neural networks is limited by their black-box nature. To overcome this drawback, we proposed an algorithm unrolling approach for LDCT denoising, namely, the cartoon-texture features guided network (CTFG-Net). The CTFG-Net integrates a cartoon sub-network, a texture sub-network, and a fusion sub-network into an end-to-end convolutional neural network model. A cartoon decomposition algorithm and a texture decomposition algorithm were unrolled to the cartoon sub-network and the texture sub-network, respectively. These two sub-networks were employed to decompose a LDCT image into its cartoon components and texture components. During the process of image decomposition, these two sub-networks exploited cartoon features and texture features to greatly suppress noise and remove artifacts in the corresponding components. At last, the final denoised results were yielded through a data fusion of the denoised cartoon components and the denoised texture components. The proposed model was tested with three datasets, Mayo dataset, Piglet dataset, and AbdomenCT-1K dataset. Qualitative results show that the CTFG-Net achieved better denoising effects for LDCT images than the competing algorithms. Compared to the competing algorithms, the proposed CTFG-Net also improved the peak signal-to-noise ratio, structural similarity index measure, and visual information fidelity by (0.3994 dB and 0.7692 dB), (0.0115 and 0.0056), and (0.0751 and 0.0433) with Mayo dataset and Piglet dataset. [ABSTRACT FROM AUTHOR]

Approximate multipliers are widely used in image processing and multimedia signal processing applications for the reduction in area, computation time, and power consumption. 4:2 compressors play a key role in multipliers for efficient addition of partial product bits. In this paper, an inexact 4:2 compressor is proposed, where a major portion of the logic associated with the generation of Carry and Sum are shared to reduce the logic/circuit complexity. During the design time overestimates are balanced with the underestimates so as to reduce the total error distance. The proposed compressor is used for the addition of partial products of the Baugh-Wooley multiplier. A novel algorithm is proposed for the placement of inexact 4:2 compressors in the partial product bit array, based on the minimum peak signal-to-noise ratio requirement of the application. The approximate multipliers thus obtained are used for edge detection using Sobel operator. It is observed from the Pareto analysis that the proposed design offers significant saving in area, computation time, and power consumption over the design with nearly the same error performance. Besides, the proposed design is more error tolerant compared with the design with nearly the same area-delay trade-off and power-delay trade-off. Moreover, the proposed inexact 4:2 compressor-based Baugh-Wooley multiplier is found to offer better accuracy-area trade-off compared to the state-of-the-art 4:2 compressors in convolutional neural network-based classification. [ABSTRACT FROM AUTHOR]

Additive manufacturing (AM) enables new possibilities for the design and manufacturing of complex metal architectures. Incorporating lattice structures into complex part geometries can enhance strength-to-weight and surface area-to-volume ratios for valuable components, particularly in industries such as medical devices and aerospace. However, lattice structures and their interconnections may result in unsupported down-skin surfaces, potentially limiting their manufacturability by metal AM technologies, such as laser powder bed fusion (LPBF). This study aimed to examine the correlation between down-skin surface area and the manufacturability of lattice structures fabricated using LPBF. Image processing algorithms were used to analyze down-skin surface areas of seven unique lattice designs and to devise quantitative metrics (such as down-skin surface area, discrete surface count, surface interconnectivity, down-skin ratio, over-print/under-print volumes, etc.) to evaluate LPBF manufacturability. The seven lattice designs were subsequently manufactured using maraging steel via LPBF and then examined using imaging using X-ray micro-computed tomography (XCT). The geometric accuracy of the lattice designs was compared with XCT scans of the manufactured lattices by employing a voxel-based image comparison technique. The results indicated a strong relationship between down-skin surface area, surface interconnectivity, and the manufacturability of a given lattice design. The digital manufacturability evaluation workflow was also applied to a medical device design, further affirming its potential industrial utility for complex geometries. [ABSTRACT FROM AUTHOR]

This paper introduces a novel thresholding and morphology-based skull stripping method for different MRI modalities. The proposed method is designed in a way which is easy to use and generates satisfactory results with minimal parameter adjustments. The method is evaluated on three different benchmark datasets and compared with nine state-of-the-art skull stripping methods. The experimental results suggest that the proposed method generates comparable results to some of the best methods in literature. However, unlike many other methods, it works well on different types of MRI scans. Moreover, this method generates the skull mask along with the brain mask that can be used to study various skull pathologies. [ABSTRACT FROM AUTHOR]

Many algorithms for image processing do not require particularly high precision, but they rely on complicated arithmetic operations for every pixel in an image. The Bernsen algorithm is a typical local thresholding algorithm for solving the problem of uneven lighting. However, this algorithm requires a significant computing overhead and is extremely sensitive to noise. In this work, two stochastic computing architectures are proposed for implementing the Bernsen algorithm by using, respectively, uncorrelated and correlated input bitstreams. Experimental results show that both designs, especially the one using correlated bitstreams, present high fault tolerance of soft errors and low hardware cost in comparison with its conventional binary implementation. However, SC logic with uncorrelated inputs is not always superior to its corresponding binary circuit in energy consumption, especially the circuit that needs long input bitstreams. That means that a reasonable use of correlation can further optimize the SC circuit design. [ABSTRACT FROM AUTHOR]

The segmentation of pathological image is an indispensable content in the cancerous diagnosis and grading, which is provided to doctors for the location and quantitative analysis of pathologically altered tissue. However, pathological whole slide image (WSI) generally has gigapixel size and huge region-level objective to be segmented. Extracting patches from WSI can address the limitation of computer memory, but the integrity of target is hence affected. Moreover, supervised learning methods require manually annotated labels for training, which is laborious and time-consuming. Thus, we studied a novel weakly supervised learning (WSL)-based end-to-end framework for semantic segmentation of cancerous area in WSI. The proposed framework is based on the block-level segmentation of convolutional neural network (CNN), while CNN is required to integrate the global average pooling layer and single fully connected layer as WSL-CNN. Class activation map and dense conditional random field (DenseCRF) are adapted to realize pixel-level segmentation of the cancerous area in patch, which is incorporated into the classification process of WSL-CNN. The hierarchically double use of DenseCRF effectively improves the precision of semantic segmentation. A region-based annotation method and a flexible method of constructing training dataset are proposed to reduce the workload of annotation. Experiments show that the block-level segmentation of CNNs has better performance than the pixel-level segmentation of fully convolutional networks, ResNet50 is the best one that achieves F1 score of 0.87426, Jaccard score of 0.78079, Recall of 0.94251 and Precision of 0.82182. The proposed framework can effectively refine the block-level prediction as semantic segmentation without pixel-level label. The precision of all tested CNNs get improved in the experiments, with WSL-ResNet50 achieving F1 score of 0.90630, Jaccard score of 0.83230, Recall of 0.92051 and Precision of 0.89789. We propose a complete end-to-end framework, including the specific structure of neural network, the construction of training dataset, the prediction method using neural network and the post-processing. CNN-like architectures can be widely transplanted into this framework to realize semantic segmentation, solving the problem of insufficient label of large-scale medical image to a certain extent. [ABSTRACT FROM AUTHOR]

• Phisically-based thermal infrared images rendering chain for artificial satellite targets. • Assessment and comparison of most relevant pixel-level VIS-TIR image fusion techniques. • Fused noisy image processing within the context of uncooperative space-craft relative navigation. State-of-the-art techniques for vision-based relative navigation rely on images acquired in the visible spectral band. Consequently, the accuracy and robustness of the navigation is strongly influenced by the illumination conditions. The exploitation of thermal-infrared images for navigation purposes is studied in the present paper, as a possible solution to improve navigation in close proximity with a target spacecraft. Thermal-infrared images depend on the thermal radiation emitted by the target, hence, they are independent from light conditions; however, they suffer from a poorer texture and a lower contrast with respect to visible ones. This paper proposes pixel-level image fusion to overcome the limitations of the two types of images. The two source images are merged into a more informative one, retaining the strengths of the distinguished sensing modalities. The contribution of this work is twofold: firstly, a realistic thermal infrared images rendering tool for artificial targets is implemented; secondly, different pixel-level visible-thermal infrared images fusion techniques are assessed through qualitative and quantitative performance metrics to ease and improve the subsequent image processing step. The work presents a comprehensive evaluation of the best fusion techniques for on-board implementation, paving the way to the development of a multispectral end-to-end navigation chain. [ABSTRACT FROM AUTHOR]

Increasing the sensitivity of image sensors is a major challenge for current imaging technology. Researchers are tackling it because highly sensitive sensors enable objects to be recognized even in dark environments, which is critical for today's smartphones, wearable devices, and automobiles. Unfortunately, conventional image-sensor architectures use light-absorptive color filters on every pixel, which fundamentally limits the detected light power per pixel. Recent advances in optical metasurfaces have led to the creation of pixelated light-transmissive color splitters with the potential to enhance sensor sensitivity. These metasurfaces can be used instead of color filters to distinguish primary colors, and unlike color filters, they can direct almost all of the incident light to the photodetectors, thereby maximizing the detectable light power. This review focuses on such metasurface-based color splitters enabling high-sensitivity color-image sensors. Their underlying principles are introduced with a focus on dispersion engineering. Then, their capabilities as optical elements are assessed on the basis of our recent findings. Finally, it is discussed how they can be used to create high-sensitivity color-image sensors. [ABSTRACT FROM AUTHOR]

In horizontal well operations, the prevalence of stuck pipe incidents is largely attributed to inadequate hole cleaning, underscoring the critical need for a thorough understanding of this process to mitigate non-productive time and financial losses. Increasing fluid velocity, the major drilling parameter of hole cleaning, diminishes the formation of cuttings beds in a wellbore. This study primarily centered on the mechanical displacement and removal of solid particles, employing advanced image processing techniques to elucidate the dynamic behavior of solid particles in deviated wellbores. The core objective of this study was to experimentally scrutinize the effects of a downhole clamp-on tool on fluid velocity to improve hole cleaning practices. To address this challenge, a customized flow loop was designed and constructed to accurately replicate the conditions encountered in horizontal wells. Pure water was used to demonstrate the effects of the clamp-on tool on cuttings transport for lightweight drilling fluid conditions. Strategically deployed, the clamp-on tool played a pivotal role in agitating cuttings, mitigating their accumulation at the bottom of the borehole. The tool's agitation mechanism noticeably improved cuttings removal by increasing velocity, extending the perturbation of cuttings transport in the tool's downstream flow, and reducing bedding formation. At lower flow rates, the tool led to an over fourfold increase in average particle velocity within the tool and a twofold increase after the tool. Our results demonstrate the substantial potential of mechanical assistance to address hole cleaning challenges and significantly advance horizontal well operations. [ABSTRACT FROM AUTHOR]

Spiking neural membrane systems (SN P systems) are a class of bio-inspired models inspired by the activities and connectivity of neurons. Extensive studies have been made on SN P systems with synchronization-based communication, while further efforts are needed for the systems with rhythm-based communication. In this work, we design an asynchronous SN P system with resonant connections where all the enabled neurons in the same group connected by resonant connections should instantly produce spikes with the same rhythm. In the designed system, each of the three modules implements one type of the three operations associated with the edge detection of digital images, and they collaborate each other through the resonant connections. An algorithm called EDSNP for edge detection is proposed to simulate the working of the designed asynchronous SN P system. A quantitative analysis of EDSNP and the related methods for edge detection had been conducted to evaluate the performance of EDSNP. The performance of the EDSNP in processing the testing images is superior to the compared methods, based on the quantitative metrics of accuracy, error rate, mean square error, peak signal-to-noise ratio and true positive rate. The results indicate the potential of the temporal firing and the proper neuronal connections in the SN P system to achieve good performance in edge detection. [ABSTRACT FROM AUTHOR]

This paper presents the methodology and theoretical foundation of topology optimization (TO) Results Spaceframe Interpreter, an automatic TO results interpreter that generates a closely associated space frame consisting of welded structural tubing or rectangular bars. TO is a computational technique that uses a finite element (FE) formulation to identify the most weight-efficient structure within a design domain. Density-based TO results in structures that take organic forms and is usually a tedious and cumbersome process to generate a computer-aided-design (CAD) model to manufacture through conventional techniques. The optimal topology frequently resembles a space frame, which is well-known as being a rigid, lightweight structure. The methodology of the TO results interpreter leverages several techniques from volumetric image processing and has four primary processes. First, the results are obtained from commercial FE/TO software and mapped into a cubic grid of voxels. Second, junction locations are extracted and member connectivity that represents a frame is identified. Third, a sizing optimization is incorporated to determine appropriate sectional dimensions of the circular or rectangular space frame members. Fourth, the optimized space frame geometry is imported into a CAD design tool to automatically create a design model. The logic and are implemented within the frame extraction processes. The automated TO interpreter is designed to interact with commercial FE analysis and CAD systems. The interpreter is demonstrated on various spatial examples including aerospace and automotive applications. In each case, the welded space frame closely resembles the TO result, with nearly equivalent stiffness and mass. [ABSTRACT FROM AUTHOR]

Image denoising and edge extraction are two main tasks in image processing. In this paper, a game model is proposed to solve the image denoising and edge extraction, which combines an adaptive improved total variation (AdITV) model for image denoising and a global sparse gradient (GSG) model for edge extraction. The AdITV model is a forward-and-backward diffusion model. In fact, forward diffusion is applied to the homogeneous region to denoise, and backward diffusion is applied to the edge region to enhance the edge. A unified explicit discrete scheme is established in this paper to solve the AdITV model, which is compatible to forward diffusion and backward diffusion. The stability of the scheme is proved. On the other hand, GSG is a functional model based on sparse representation, which is robust to extract edges under the influence of noise. AdITV and GSG are chosen as two components of the game model. The alternate iteration method is used to solve the game problem. The convergence of the algorithm is proved and numerical experiments show the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Conventional photography can only provide a two-dimensional image of the scene, whereas emerging imaging modalities such as light field enable the representation of higher dimensional visual information by capturing light rays from different directions. Light fields provide immersive experiences, a sense of presence in the scene, and can enhance different vision tasks. Hence, research into light field processing methods has become increasingly popular. It does, however, come at the cost of higher data volume and computational complexity. With the growing deployment of machine-learning and deep architectures in image processing applications, a paradigm shift toward learning-based approaches has also been observed in the design of light field processing methods. Various learning-based approaches are developed to process the high volume of light field data efficiently for different vision tasks while improving performance. Taking into account the diversity of light field vision tasks and the deployed learning-based frameworks, it is necessary to survey the scattered learning-based works in the domain to gain insight into the current trends and challenges. This paper aims to review the existing learning-based solutions for light field imaging and to summarize the most promising frameworks. Moreover, evaluation methods and available light field datasets are highlighted. Lastly, the review concludes with a brief outlook for future research directions. [ABSTRACT FROM AUTHOR]

Background: Plants are known to be infected by a wide range of pathogenic microbes. To study plant diseases caused by microbes, it is imperative to be able to monitor disease symptoms and microbial colonization in a quantitative and objective manner. In contrast to more traditional measures that use manual assignments of disease categories, image processing provides a more accurate and objective quantification of plant disease symptoms. Besides monitoring disease symptoms, computational image processing provides additional information on the spatial localization of pathogenic microbes in different plant tissues. Results: Here we report on an image analysis tool called ScAnalyzer to monitor disease symptoms and bacterial spread in Arabidopsis thaliana leaves. Thereto, detached leaves are assembled in a grid and scanned, which enables automated separation of individual samples. A pixel color threshold is used to segment healthy (green) from chlorotic (yellow) leaf areas. The spread of luminescence-tagged bacteria is monitored via light-sensitive films, which are processed in a similar manner as the leaf scans. We show that this tool is able to capture previously identified differences in susceptibility of the model plant A. thaliana to the bacterial pathogen Xanthomonas campestris pv. campestris. Moreover, we show that the ScAnalyzer pipeline provides a more detailed assessment of bacterial spread within plant leaves than previously used methods. Finally, by combining the disease symptom values with bacterial spread values from the same leaves, we show that bacterial spread precedes visual disease symptoms. Conclusion: Taken together, we present an automated script to monitor plant disease symptoms and microbial spread in A. thaliana leaves. The freely available software (https://github.com/MolPlantPathology/ScAnalyzer) has the potential to standardize the analysis of disease assays between different groups. [ABSTRACT FROM AUTHOR]

AbstractFresh Oudemansiella raphanipies are rich in protein and prone to deterioration during natural storage. Hot air drying is typically used to extend shelf life. However, some O. raphanipies may not dry during the actual drying process because of different placements, which can adversely affect the entire product. To detect dryness, we introduced ORD-Net, a model based on RGB images captured using a smartphone camera. Incorporating residual hybrid dilated convolution and efficient channel attention modules, ORD-Net outperforms mainstream algorithms, achieving high accuracy, precision, recall, F1-score, and a Matthews coefficient of 85.3, 82.2, 91.2, 86.5%, and 0.709, respectively. Additionally, experiments on various CPUs confirm its adaptability for industrial use, with AMD Ryzen CPUs performing optimally with an average processing time of 0.67 s for a single target. This study proposes a convenient and cost-effective identification method that can effectively determine the drying status of O. raphanipies, thus laying the foundation for the high-throughput identification of the drying conditions of postharvest O. raphanipies. The data and methods used in this study are available at https://github.com/Jmin-Zhao/ORDNet. [ABSTRACT FROM AUTHOR]

The article explores advanced image processing techniques for pigment discrimination in rock art paintings, emphasizing color separation using RGB (red, green, blue) and LHCUv (Luminance, Hue, Chroma) imagery. It highlights the use of dimensionality reduction methods such as Principal Components Analisys PCA and Independent Component Analysis (ICA), with a focus on Gaussian Mixture Models (GMM) for probabilistic classification of image elements. This approach, applied to the Chomache archaeological site on the northernmost coast of the Atacama Desert in Chile, reveals previously undetected motifs and details, offering a nuanced perspective in rock art documentation and analysis. This proposal reinforces the value of rock art panel not only as a finished product but as a process. [ABSTRACT FROM AUTHOR]

The extraction of cellular structure feature on the spherical premixed flame surface faces accuracy challenges. The Schlieren technique was employed to obtain the hydrogen-air premixed spherical flames images in a constant volume vessel at room temperature and atmospheric pressure under an equivalent ratio of 0.8 in this work. A bio-inspired Cellpose 2.0, driven by deep learning, is innovatively introduced to train the cell segmentation model in the combustion field. After labeling and training cells of different shapes and sizes, an efficient and accurate model suitable for cell feature extraction was finally obtained to identify and quantify various cells characteristics, such as number, size, and distribution. Results show that the average precision (AP) during the model online pre-training process reaches 0.625. Meanwhile, the critical flame radius of transition acceleration obtained is 36 mm and the crack length tends to grow linearly after the flame radius exceeds this critical point. Additionally, the average cell area gradually converges to a stable value after the flame radius exceeds the uniform cellularity critical radius. The cell segmentation model obtained in this work can be further used to train different spherical flames under various conditions, helping to develop hydrogen combustion and explosion modelling. [Display omitted] • First application of Cellpose 2.0 in combustion image process yields AP of 0.625 • Quantitative cell information on H 2 -Air flame surfaces achieved with deep learning. • Cells number rapid increase after the flame exceeds critical radius of transition acceleration. • Average cell area gradually converges to a stable value after uniform cellularity critical radius. • Flame propagation exhibits a self-accelerating trend after transition acceleration critical radius. [ABSTRACT FROM AUTHOR]