Search

We report on the construction of the SiRO—SiPM ReadOut muon detector, a detection system based on plastic scintillator bars designed for muography applications. Using six 1 m 2 layers of active medium, grouped two by two into three rectangular matrices of pixels, each separated by a variable distance, the spatial coordinates of the muon's impact point on every matrice are obtained and used for trajectory reconstruction. Validation studies have been performed using Monte Carlo simulations and later confirmed by preliminary measurements in our laboratory and in underground, in the Slănic Prahova salt mine, in Romania. [ABSTRACT FROM AUTHOR]

Time-resolved photoemission electron microscopy (PEEM) has established itself as a versatile experimental technique to unravel the ultrafast electron dynamics of materials with nanometer-scale resolution. However, the approach of performing PEEM-based, pixel-by-pixel lifetime mapping has not been reported thus far. Herein, we describe in detail the data pre-processing procedure and an algorithm to perform time-trace fittings of each pixel. We impose an energy cutoff for each pixel prior to spectral integration to enhance the robustness of our approach. With the energy cutoff, the energy-integrated time traces show improved statistics and lower fitting errors, thus resulting in a more accurate determination of the fit parameters, e.g., decay time constants. Our work allows us to reliably construct PEEM-based lifetime maps, which potentially shed light on the effects of local microenvironment on the ultrafast processes of the material and allow spatial distributions of lifetimes to be correlated with observables obtained from complementary microscopic techniques, hence enabling a more comprehensive characterization of the material. [ABSTRACT FROM AUTHOR]

Saliency maps are input-resolution matrices used for visualizing local interpretations of image classifiers. Their pixel values reflect the importance of corresponding image locations for the model's decision. Despite numerous proposals on how to obtain such maps, their evaluation remains an open question. This paper presents a carefully designed experimental procedure along with a set of quantitative interpretation evaluation metrics that rely solely on the original model behavior. Previously noticed evaluation biases have been attenuated by separating locations with high and low values, considering the full saliency map resolution, and using classifiers with diverse accuracies and all the classes in the dataset. We used the proposed evaluation metrics to compare and analyze seven well-known interpretation methods. Our experiments confirm the importance of object background as well as negative saliency map pixels, and we show that the scale of their impact on the model is comparable to that of positive ones. We also demonstrate that a good class score interpretation does not necessarily imply a good probability interpretation. DeepLIFT and LRP- ϵ methods proved most successful altogether, while Grad-CAM and Ablation-CAM performed very poorly, even in the detection of positive relevance. The retention of positive values alone in the latter two methods was responsible for the inaccurate detection of irrelevant locations as well. [ABSTRACT FROM AUTHOR]

The peg-in-hole task is important in robotics. Visual inspection is a crucial method for recognition and positioning during this task. Currently, vision-based peg-in-hole techniques suffer from limited applicability and low positioning accuracy. Therefore, this study introduced a general vision-based approach for robotic peg-in-hole tasks. This approach delineates the process into two stages. First, during the object recognition, positioning, and approach phases, a coarse adjustment technique for the assembly pose of the robot's end effector was proposed based on object recognition. This method determines the pose of the hole to be assembled through ellipse fitting, thereby guiding the robot to approach the hole. Second, a Q-learning-based method was introduced to fine adjust the robot end effector's pose and position. Q-learning was applied to the scenario of small-scale adjustment of the robotic peg-in-hole, the reward function based on the pixel area of the gap and the included angle between central axes of peg and hole are designed. Finally, the feasibility and efficacy of this method are substantiated through a series of assembly experiments. [ABSTRACT FROM AUTHOR]

In the multi-focus image fusion process, generating a focus decision map is typically a requisite step before the actual fusion of images. Many multi-focus image fusion methods often require optimization through post-processing techniques such as hole filling and removal of small regions in the decision map. To solve these problems and obtain better fusion images, we propose a multi-focus image fusion algorithm based on an end-to-end decision optimization model called EDOM-MFIF. Firstly, we design a cross-scale feature extraction encoder based on the joint attention fusion of upper and lower information, which can fully extract the shallow texture information and high-level semantic information of images. Secondly, we design a feature fusion module using convolution and spatial attention for comprehensive feature fusion and maximal retention of global image information. Finally, we achieve end-to-end training and optimization of the focusing decision map by integrating the decision map's optimization into the whole image fusion architecture. This prevents evident pixel faults in the immediate area from spreading to other areas during post-processing, which could lead to inaccurate classification findings, in addition to maintaining pixel consistency with the original image to the greatest extent possible. To facilitate training of the multi-focus image fusion model, we construct a large-scale multi-focus image dataset with a supervised decision map and test the algorithm on three different types of public datasets. The experimental results show that the proposed algorithm outperforms other advanced multi-focus image fusion algorithms in both objective evaluation and visual evaluation. [ABSTRACT FROM AUTHOR]

When the data distributions between the source and target domains are inconsistent, unsupervised cross domain object detection improves the performance of the detector without the need to add any additional annotation information. However, existing advanced methods overlook the semantic consistency of images, which leads to incorrect transfer knowledge in feature learning and reduces adaptive performance. Therefore, we propose a feature correlation learning method, called Semantic Consistency Knowledge Transfer (SCKT) for unsupervised cross domain object detection, which focuses on similar semantic information and achieves fine-grained corresponding scales domain adaptation. Specifically, we design a Multi-channel Adaptive Correction (MAC) module for image enhancement, which alleviates pixel distortion and maintains semantic consistency. Furthermore, the proposed Related Knowledge Mining (RKM) module consists of Feature Correlation Learning (FCL) and Consistent Knowledge Learning (CKL), which use generated semantic consistency features to capture different levels of image details and semantic information, achieving corresponding domain alignment at multiple levels. Most importantly, SCKT does not rely on a specific network structure, and does not reduce inference speed, which is suitable for different object detectors. Extensive experiments show that our SCKT can exhibit optimal performance in multiple domain migration scenarios. Especially for the challenging PASCAL VOC → Clipart, SCKT generates 54.6% mAP. [ABSTRACT FROM AUTHOR]

Summary: This paper develops a new image encryption algorithm based on a novel two‐dimensional chaotic map and bit‐level dynamic scrambling. First, multiple one‐dimensional chaotic maps are coupled to construct a novel two dimensions Logistic‐Sine‐coupling chaos map (2D‐LSCCM). The performance analysis shows that the 2D‐LSCCM has more complex chaotic characteristics and wider chaotic range than many extant 2D chaos maps. Second, original image matrix combines with hash algorithm SHA‐256 to generate a hash value. The initial values of 2D‐LSCCM are generated based on the hash value. Third, the original image matrix is divided into multiple sub‐matrices by wavelet transform, followed by scrambling by an improved Knuth shuffle algorithm. Fourth, the scrambled multiple sub‐matrices are stitched into an image matrix of M×N×3$$ M\times N\times 3 $$ and converted into a binary matrix. The chaotic sequence generated by 2D‐LSCCM is introduced as a control sequence to control the bit‐level scrambling of pixel points, which realizes the bit‐level dynamic scrambling. Finally, the diffusion operation is performed by parameter par and chaotic sequence to obtain the final encrypted image. The algorithm security analysis and simulation examples demonstrate the effectiveness of the proposed encryption scheme. [ABSTRACT FROM AUTHOR]

Single-pixel detectors are popular devices in optical sciences because of their fast temporal response, high sensitivity, and low cost. However, when being used for imaging, they face a fundamental challenge in acquiring high-dimensional information of an optical field because they are essentially zero-dimensional sensors and measure only the light intensity. To address this problem, we developed a cascaded compressed-sensing single-pixel camera, which decomposes the measurement into multiple stages, sequentially reducing the dimensionality of the data from a high-dimensional space to zero dimension. This measurement scheme allows us to exploit the compressibility of a natural scene in multiple domains, leading to highly efficient data acquisition. We demonstrated our method in several demanding applications, including enabling tunable single-pixel full-waveform hyperspectral light detection and ranging (LIDAR) for the first time. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel scan driver combined with a logic circuit using amorphous indium‐gallium‐zinc‐oxide (a‐InGaZnO) thin‐film transistors (TFTs) in order to enhance the electrical stability and reduce power consumption in display panels. The latest mobile displays with high resolution and refresh rates consume more battery power, which inevitably limits portability and usability. The proposed scan driver can mask the signal by combining the output stage with a logic circuit, thereby blocking the output pulse for static images. This allows the display panel to operate in a partial driving mode depending on the display content. Due to the masking of the scan driver's output pulses, the connected pixel circuits are consistently maintained in the same state as the previous frame, leading to a lower refresh rate and reduced power consumption. Furthermore, by constructing additional control signals, the proposed scan driver can operate stably in depletion mode under a ∆VTH = −3 V. [ABSTRACT FROM AUTHOR]

Micro-light-emitting diodes offer vibrant colors and energy-efficient performance, holding promise for next-generation inorganic displays. However, their widespread adoption requires the development of cost-effective chips and low-defect pixelation processes. Addressing these challenges, nanorod-light-emitting diodes utilize inkjet and dielectrophoretic assembly techniques. Nevertheless, the small volume and edge-directed emission of nanorod-light-emitting diodes necessitate brightness and light extraction improvements. As an alternative, we propose dielectrophoretic-friendly fin-light-emitting diodes, designed to enhance brightness and light extraction efficiency through face-selective dielectrophoretic assembly technology. Our results confirm the potential for next-generation inorganic displays, with a wafer utilization ratio exceeding 90%, a vertical assembly ratio of 91.3%, and a pixel production yield of 99.93%. Moreover, blue fin-light-emitting diodes achieve an external quantum efficiency of 9.1% and a brightness of 8640 cd m−2 at 5.0 V, which, even at this early stage, are comparable to existing technologies. Lee et al. report blue fin-LEDs with improved brightness and light extraction efficiency comparing to nanorod-LEDs by using a face-selective dielectrophoretic assembly technology. The wafer utilization ratio exceeds 90%, with a vertical assembly ratio of 91.3% and pixel production yield of 99.93%. [ABSTRACT FROM AUTHOR]

Small‐size pixels and high efficiency under low injection levels are required for high‐resolution microdisplay. Efficient blue InGaN micro‐light‐emitting diodes (μLEDs) with 5 μm diameter are fabricated using AuSn flip‐chip bonding, high reflection electrodes, and large‐area N electrodes surrounding the mesas. The peak external quantum efficiency (EQE) measured in an integrating sphere is as high as 13.67% at a current density of 5.4 A cm−2. Moreover, at a current density of 0.1 A cm−2, EQE can still reach 11.69%. The electrical efficiency approaches 1, and the differential slope of log L versus log I is close to 1 at low current density. These results suggest significant progress in exploring high‐efficiency 5 μm InGaN blue μLEDs. [ABSTRACT FROM AUTHOR]

A common cause of deterioration in historic manuscripts is ink transparency or bleeding from the opposite page. Philologists and paleographers can significantly benefit from minimizing these interferences when attempting to decipher the original text. Additionally, computer-aided text analysis can also gain from such text enhancement. In previous work, we proposed the use of neural networks (NNs) in combination with a data model that characterizes the damage when both sides of a page have been digitized. This approach offers the distinct advantage of allowing the creation of an artificial training set that teaches the NN to differentiate between clean and damaged pixels. We tested this concept using a shallow NN, which proved effective in categorizing texts with varying levels of deterioration. In this study, we adapt the NN design to tackling remaining classification uncertainties caused by areas of text overlap, inhomogeneity, and peaks of degradation. Specifically, we introduce a new output class for pixels within overlapping text areas and incorporate additional features related to the pixel context information to promote the same classification for pixels adjacent to each other. Our experiments demonstrate that these enhancements significantly improve the classification accuracy. This improvement is evident in the quality of both binarization, which aids in text analysis, and virtual restoration, aimed at recovering the manuscript's original appearance. Tests conducted on a public dataset, using standard quality indices, reveal that the proposed method outperforms both our previous proposals and other notable methods found in the literature. [ABSTRACT FROM AUTHOR]

Surface water fraction mapping is an essential preprocessing step for the subpixel mapping (SPM) of surface water, providing valuable prior knowledge about surface water distribution at the subpixel level. In recent years, spectral mixture analysis (SMA) has been extensively applied to estimate surface water fractions in multispectral images by decomposing each mixed pixel into endmembers and their corresponding fractions using linear or nonlinear spectral mixture models. However, challenges emerge when introducing existing surface water fraction mapping methods to hyperspectral images (HSIs) due to insufficient exploration of spectral information. Additionally, inaccurate extraction of endmembers can result in unsatisfactory water fraction estimations. To address these issues, this paper proposes an adaptive unmixing method based on iterative multi-objective optimization for surface water fraction mapping (IMOSWFM) using Zhuhai-1 HSIs. In IMOSWFM, a modified normalized difference water fraction index (MNDWFI) was developed to fully exploit the spectral information. Furthermore, an iterative unmixing framework was adopted to dynamically extract high-quality endmembers and estimate their corresponding water fractions. Experimental results on the Zhuhai-1 HSIs from three test sites around Nanyi Lake indicate that water fraction maps obtained by IMOSWFM are closest to the reference maps compared with the other three SMA-based surface water fraction estimation methods, with the highest overall accuracy (OA) of 91.74%, 93.12%, and 89.73% in terms of pure water extraction and the lowest root-mean-square errors (RMSE) of 0.2506, 0.2403, and 0.2265 in terms of water fraction estimation. This research provides a reference for adapting existing surface water fraction mapping methods to HSIs. [ABSTRACT FROM AUTHOR]

In recent years, several superpixel-segmentation methods have been developed to efficiently segment noisy images. However, these methods still face challenges such as high computational complexity and poor adaptability. Therefore, this paper develops a novel superpixel-based robust segmentation model including two modules: superpixel generation and superpixel-based image segmentation. In the superpixel generation module, a fuzzy factor containing local spatial information of pixels is introduced into fuzzy possibilistic clustering algorithm with local search. In the superpixel-based segmentation module, a superpixel-based fuzzy C-means algorithm with local spatial information of superpixels is proposed, which nonlinearly combines the membership of superpixels with the membership of their neighboring superpixels. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art segmentation algorithms in terms of evaluation indexes and visual effects. [ABSTRACT FROM AUTHOR]

Recent self-supervised contrastive learning methods are powerful and efficient for robust representation learning, pulling semantic features from different cropping views of the same image while pushing other features away from other images in the embedding vector space. However, model training for contrastive learning is quite inefficient. In the high-dimensional vector space of the images, images can differ from each other in many ways. We address this problem with heuristic attention pixel-level contrastive loss for representation learning (HAPiCLR), a self-supervised joint embedding contrastive framework that operates at the pixel level and makes use of heuristic mask information. HAPiCLR leverages pixel-level information from the object's contextual representation instead of identifying pair-wise differences in instance-level representations. Thus, HAPiCLR enhances contrastive learning objectives without requiring large batch sizes, memory banks, or queues, thereby reducing the memory footprint and the processing needed for large datasets. Furthermore, HAPiCLR loss combined with other contrastive objectives such as SimCLR or MoCo loss produces considerable performance boosts on all downstream tasks, including image classification, object detection, and instance segmentation. [ABSTRACT FROM AUTHOR]

Recent advances in the development of cryogenic particle detectors such as magnetic microcalorimeters allow the fabrication of sensor arrays with an increasing number of pixels. Since these detectors must be operated at the lowest temperatures, the readout of large detector arrays is still quite challenging. This is especially true for the ECHo experiment, which presently aims to simultaneously run 6,000 two pixel detectors to investigate the electron neutrino mass. For this reason, we developed a readout system based on a microwave SQUID multiplexer (μ MUX) that is operated by a custom software-defined radio (SDR) at room-temperature. The SDR readout electronics consist of three distinct hardware units: a data processing board with a Xilinx ZynqUS+ MPSoC; a converter board that features DACs, ADCs, and a coherent clock distribution network; and a radio frequency front-end board to translate the signals between the baseband and the microwave domains. Here, we describe the characteristics of the full-scale SDR system. First, the generated frequency comb for driving the μ MUX was evaluated. Subsequently, by operating the SDR in direct loopback, the crosstalk of the individual channels after frequency demultiplexing was investigated. Finally, the system was used with a 16-channel μ MUX to evaluate the linearity of the SDR, and the noise contributed to the overall readout setup. [ABSTRACT FROM AUTHOR]

In this paper, the proposal for a new multichroic pixel camera for the QUBIC instrument is presented, which aims to measure the B-mode polarization of the cosmic microwave background. The camera features antenna-coupled magnetic microbolometers (MMB) read out by a microwave SQUID multiplexer and software-defined radio-based room-temperature electronics, which are specifically optimized for MMB readout. The architecture of the detectors and their readout system is introduced, and the main design considerations are also discussed. The initial results of the simulation study suggest that MMBs are capable of achieving background-limited detection of the sky when used in an instrument like QUBIC. Additionally, the time response of these detectors appears to be sufficiently fast for the given telescope scan speed and beam size. [ABSTRACT FROM AUTHOR]

Image comparison is a fundamental step for monitoring images and has wide applications in many disciplines of sciences, including satellite imaging, medical research, quality control and so forth. This problem, however, is complicated because (i) the observed images often contain noise, (ii) the image intensity functions are discontinuous and have spatial structures. In the literature, a vast majority of the methods are intensity-based. However, such an approach is often questionable in real life situations where small changes in the background may not indicate an actual meaningful change in the images as long as the boundaries of the image objects remain the same. In this article, we propose a flexible and effective image comparison method based on local pixel clustering and construct a test statistic based on the Variation of Information metric. This is a feature based image comparison technique where edges or the jump points are considered as the primary features. Numerical examples and statistical properties show that the proposed image comparison method performs well in various real life scenarios. [ABSTRACT FROM AUTHOR]

We investigate algorithms for testing whether an image is connected. Given a proximity parameter ϵ ∈ (0 , 1) and query access to a black-and-white image represented by an n × n matrix of Boolean pixel values, a (1-sided error) connectedness tester accepts if the image is connected and rejects with probability at least 2/3 if the image is ϵ -far from connected. We show that connectedness can be tested nonadaptively with O (1 ϵ 2 ) queries and adaptively with O (1 ϵ 3 / 2 log 1 ϵ ) queries. The best connectedness tester to date, by Berman, Raskhodnikova, and Yaroslavtsev (STOC 2014) had query complexity O (1 ϵ 2 log 1 ϵ) and was adaptive. We also prove that every nonadaptive, 1-sided error tester for connectedness must make Ω (1 ϵ log 1 ϵ) queries. [ABSTRACT FROM AUTHOR]

While reinforcement learning has shown promising abilities to solve continuous control tasks from visual inputs, it remains a challenge to learn robust representations from high-dimensional observations and generalize to unseen environments with distracting elements. Recently, strong data augmentation has been applied to increase the diversity of the training data, but it may damage the task-relevant pixels and thus hinder the optimization of reinforcement learning. To this end, this paper proposes temporal prediction model with context-aware data augmentation (TPMC), a framework which incorporates context-aware strong augmentation into the dynamic model for learning robust policies. Specifically, TPMC utilizes the gradient-based saliency map to identify and preserve task-relevant pixels during strong augmentation, generating reliable augmented images for stable training. Moreover, the temporal prediction consistency between strong and weak augmented views is enforced to construct a contrastive objective for learning shared task-relevant representations. Extensive experiments are conducted to evaluate the performance on DMControl-GB benchmarks and several robotic manipulation tasks. Experimental results demonstrate that TPMC achieves superior data-efficiency and generalization to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by 4. 5 % and 5. 0 %. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to 1 1 % for the binary image segmentation approach. [ABSTRACT FROM AUTHOR]

The scale of white foreign fibers in bobbin yarn is small, resulting in multiple types of data imbalance in the dataset. These imbalances include a severe imbalance of foreign fiber pixels compared to background pixels and an imbalance in the size target scale. Consequently, conventional semantic segmentation networks struggle to segment these fibers effectively. First, in tackling the scarcity of white foreign fiber instances within bobbin yarn samples, this research utilizes original foreign fiber images to train the DCGAN and generate adequate training samples. Secondly, a multiscale residual U-Net is constructed to extract foreign fiber features from different scales. The network is encouraged to learn semantic features at each scale and each layer of the decoding stage. This overcomes the problem of scale imbalance in the foreign fiber dataset and enhances the model's capability to extract weak semantic information from small targets. Thirdly, a weighted binary cross-entropy loss function is integrated into the network's training phase to rectify the class imbalance and refine segmentation performance. This function adjusts the weighting of foreign fiber pixel data, thereby addressing the disproportionate distribution between foreign fibers and background pixels within the dataset. Finally, the proposed method is experimentally validated using a dataset of white foreign fibers. The experimental results show that the proposed method achieves better results in the critical evaluation metrics, as evidenced by the accuracy of 97.52 %, the MIoU of 95.26 %, the DICE coefficient of 81.29 %, and the F1 Score of 84.92 %. These statistics demonstrate the method's efficacy in achieving high-precision segmentation of white foreign fibers. [ABSTRACT FROM AUTHOR]

The pigments of cultural color paintings have faded with the passage of time. Color segmentations are essential for digital color reconstruction, but the complexity of color paintings makes it challenging to achieve high-precision segmentation using previous methods. To address the challenges of color painting segmentation, an optimized strategy based on U-Net is proposed in this paper. The residual blocks of a residual network (ResNet) are added to the original U-Net architecture, and a UR-Net is constructed for the semantic segmentation of color paintings. The following steps are taken. First, datasets of color paintings are obtained as training and test samples and are labeled with the two following pixel colors: earth red and ultramarine blue. Second, residual blocks are improved and added to fit the U-Net architecture. Then, a UR-Net is constructed and trained using the samples to obtain the semantic segmentation model. Finally, the effectiveness of the trained UR-Net model for segmenting the test samples is evaluated, and it is compared with the K-means clustering algorithm, ResNet, and U-Net. Data from several studies suggest that the segmentation accuracy of the UR-Net model is higher than that of other methods for the color segmentation of painted images, and the IoUs of the segmented earth red and ultramarine blue pixels are 0.9346 and 0.9259, respectively, achieving the desired results. The proposed UR-Net model provides theoretical and methodological support for further in-depth research on color recognition and segmentation of cultural color paintings. [ABSTRACT FROM AUTHOR]

A light-field display with a near-virtual-image mode, which employs both a lens array and an aperture array, was previously proposed to provide a wide viewing zone angle and bright three-dimensional (3D) images. However, it is desirable to enhance its resolutions, which are presently equal to those of conventional displays. Thus, we proposed a technique for increasing the resolutions of 3D images generated by the light-field display with the near-virtual-image mode. The gap between the flat-panel display and lens array is reduced to decrease the magnification of the virtual images of the pixels and to enable the observation of multiple virtual pixel images through each lens. Further, we imaged the aperture array using the lens array to eliminate the gaps between the multiple pixels observed through adjacent lenses. We constructed a prototype display based on the proposed technique and verified the increase in the resolution of the prototype display compared to the original near-virtual-image light-field display. [ABSTRACT FROM AUTHOR]

Crack detection or segmentation on concrete structures is a vital process in structural health monitoring (SHM). Though supervised machine learning techniques have gained tremendous success in this domain, data collection and annotation continue to be challenging. Image data collection is challenging, tedious, and laborious, including accessing representative datasets and manually labeling training data in the SHM domain. According to the literature, there are significant issues with the hand-annotation of image data. To address this gap, this paper proposes a two-stage weakly supervised learning framework utilizing a novel "crack attention network (CrANET)" with attention mechanism to detect and segment cracks on images with no human annotations in pixel-level labels. This framework classifies concrete surface images into crack or no-cracks and then uses gradient class activation mapping visualization to generate crack segmentation. Professionals and domain experts subsequently evaluate these segmentation results via a human expert validation study. As the literature suggests that weakly supervised learning is a limited practice in SHM, this research title will motivate researchers in SHM to research and develop a weakly supervised learning approach processing as state of the art. [ABSTRACT FROM AUTHOR]

Sparsely annotated image segmentation has gained popularity due to its ability to significantly reduce the labeling burden on training data. However, existing methods still struggle to learn complete object structures, especially for complex shadow objects. This paper discusses two prevalent issues existing in previous methods, i.e., generating noisy pseudo labels and misdetecting ambiguous regions. To tackle these challenges, we propose a novel weakly-supervised learning framework to boost sparsely annotated shadow detection. Concretely, a reliable label propagation (RLP) scheme is first designed to diffuse sparse annotations into unlabeled regions, thereby generating denser pseudo shadow masks. This scheme effectively reduces the number of noisy labels by incorporating uncertainty analysis. Then, a multi-cue semantic calibration (MSC) strategy is presented to refine the semantic features extracted from the backbone by employing edge, global, and adjacent priors. Embedded with MSC, the detection network becomes more discriminative against ambiguous regions. By combining RLP and MSC, the proposed weakly-supervised framework can detect complete and accurate shadow regions from sparse annotations. Experimental results on three benchmark datasets demonstrate that our method achieves comparable performance to recent fully-supervised methods, while requiring only about 4.5% of the pixels to be labeled. Boosting sparsely annotated shadow detection [ABSTRACT FROM AUTHOR]

Protecting data transmission, which plays a capital importance for data confidentiality, has recently been recognized as significant attention. Several research works using the data hiding paradigm have tried to apply steganography in digital images to protect the secret bits of confidential data against unwanted access throughout the public network commonly used. Nevertheless, the existing steganography algorithm faces a common challenge of a significant distortion of the image transmitted through the public network after concealing the secret bits in its pixels. To address this steganography problem in digital images, this article presents a new algorithm to optimize embeddable pixels used to yield a quality stego image with fewer distortions. The proposed method transforms the secret bits into a simplified format by changing the base system and mathematical sorting to reduce the magnitude, making the payload size significantly minimal. The proposed method is experimentally tested using 256 x 256 grayscale images from the Signal and Image Processing Institute (SIPI) database as cover images and random bits generated from Lorem Ipsum text as secret data. The method's performance is compared to the recent Difference Expansion (DE) method, showing superior results with an average Peak Signal-to-Noise Ratio (PSNR) of 85 dB and a Structural Similarity Index Measure (SSIM) of 0.99, indicating higher stego image quality. [ABSTRACT FROM AUTHOR]

Introduction: Fast, accurate, and automatic analysis of histopathological images using digital image processing and deep learning technology is a necessary task. Conventional histopathological image analysis algorithms require the manual design of features, while deep learning methods can achieve fast prediction and accurate analysis, but rely on the drive of a large amount of labeled data. Methods: In this work, we introduce WSSS-CRAM a weakly-supervised semantic segmentation that can obtain detailed pixel-level labels from image-level annotated data. Specifically, we use a discriminative activation strategy to generate category-specific image activation maps via class labels. The category-specific activation maps are then post-processed using conditional random fields to obtain reliable regions that are directly used as ground-truth labels for the segmentation branch. Critically, the two steps of the pseudo-label acquisition and training segmentation model are integrated into an end-to-end model for joint training in this method. Results: Through quantitative evaluation and visualization results, we demonstrate that the framework can predict pixel-level labels from image-level labels, and also perform well when testing images without image-level annotations. Discussion: Future, we consider extending the algorithm to different pathological datasets and types of tissue images to validate its generalization capability. [ABSTRACT FROM AUTHOR]

Accurately identifying clouds in satellite images is an important stage in processing such images for scientific use. Cloudy image pixels are labelled using a pixel mask, to allow them to be filtered out and ignored. The accuracy at which ‘cloud masking’ can be performed needs to be determined and this is often done by expert manual classification. Given the public enthusiasm for weather, we tested whether this classification could be performed reliably by ‘citizen scientists’. We found that the public could identify cloud with a 94% accuracy over ocean. Our analysis pointed to future improvements of the CloudCatcher project. [ABSTRACT FROM AUTHOR]

The exponential growth of data from sensors and internet‐connected devices has challenged traditional electronic computing, particularly in processing speed and power efficiency. Optical information processing, with its inherent high speed and parallelism, offers a promising solution. Moreover, optical processing is vital for developing all‐optical networks, where all‐optical imaging is essential. In this paper, a novel all‐optical imaging technique that leverages in situ anion exchange reactions between perovskite nanocrystals to create an array of pixels with tunable emission wavelengths is proposed. This method enables the conversion of UV light, whether transmitted or reflected by an object, into the visible spectrum, thereby establishing a direct correlation between spectral and spatial information. By employing wavelength division multiplexing (WDM), the approach reduces the dimensionality of information acquisition from two dimensions to one, enhancing imaging speed. This innovation paves the way for significant advancements in all‐optical imaging and image processing, offering new possibilities for faster and more efficient imaging technologies. [ABSTRACT FROM AUTHOR]

Data Augmentation (DA) is significant for Hyperspectral Image (HSI) classification especially in the case of limited labeled training data. Various DA models have been introduced to augment HSI data by using image processing techniques, prior knowledge or contextual information of HSI. However, spatial information in HSI could be inefficiently adopted in these DA models, leading to the lack of diversity and richness of the augmented data. To handle the issue, inspired by the recently proposed Principal Component Analysis based DA (PCA-DA) and Superpixelwise PCA (SuperPCA), we introduce SuperPCA based DA (SuperPCA-DA) in this paper. Specifically, an HSI is firstly divided into various superpixel blocks by typical image segmentation techniques, followed by fixed-size window and superpixel based local reconstruction for HSI denoising, and then the proposed SuperPCA-DA is employed in each superpixel block for HSI data augmentation where PCA is locally conducted in each superpixel to extract low-dimensional features, which will be projected back onto the original high-dimensional spectral space with random noises added into the projection matrix of PCA. The novel DA model can effectively generate new samples with diversity and richness by employing superpixels based spatial information of HSI, which could outperform classic and state-of-the-art DA models and then improve the accuracy of the subsequent classification models, especially when the number of training data is limited. The experimental results on three HSI datasets demonstrate the effectiveness of the proposed method. The code of the proposed model is available at https://github.com/XinweiJiang/SuperPCA-DA. [ABSTRACT FROM AUTHOR]

Fingerprint liveness detection systems have been affected by spoofing, which is a severe threat for fingerprint-based biometric systems. Therefore, it is crucial to develop some techniques to distinguish the fake fingerprints from the real ones. The software based techniques can detect the fingerprint forgery automatically. Also, the scheme shall be resistant against various distortions such as noise contamination, pixel missing and block missing, so that the forgers cannot deceive the detector by adding some distortions to the faked fingerprint. In this paper, we propose a fingerprint forgery detection algorithm based on a suggested adaptive thresholding pattern. The anisotropic diffusion of the input image is passed through three levels of the wavelet transform. The coefficients of different layers are adaptively thresholded and concatenated to produce the feature vector which is classified using the SVM classifier. Another contribution of the paper is to investigate the effect of various distortions such as pixel missing, block missing, and noise contamination. Our suggested approach includes a novel method that exhibits improved resistance against a range of distortions caused by environmental phenomena or manipulations by malicious users. In quantitative comparisons, our proposed method outperforms its counterparts by approximately 8% and 5% in accuracy for missing pixel scenarios of 90% and block missing scenarios of size 70 × 70 , respectively. This highlights the novelty approach in addressing such challenges. [ABSTRACT FROM AUTHOR]

Camera-based relative pose estimation (RPE) localizes a mobile robot given a view at the current position and an image at a reference location. Matching the landmarks between views is critical to localization quality. Common challenges are appearance changes, for example due to differing illumination. Indirect RPE methods extract high-level features that provide invariance against appearance changes but neglect the remaining image data. This can lead to poor pose estimates in scenes with little detail. Direct RPE methods mitigate this issue by operating on the pixel level with only moderate preprocessing, but invariances have to be achieved by different means. We propose to attain illumination invariance for the direct RPE algorithm MinWarping by integrating it with a convolutional neural network for image preprocessing, creating a hybrid architecture. We optimize network parameters using a metric on RPE quality, backpropagating through MinWarping and the network. We focus on planar movement, panoramic images, and indoor scenes with varying illumination conditions; a novel dataset for this setup is recorded and used for analysis. Our method compares favourably against the previous best preprocessing method for MinWarping, edge filtering, and against a modern deep-learning-based indirect RPE pipeline. Analysis of the trained hybrid architecture indicates that neglecting landmarks in a direct RPE framework can improve estimation quality in scenes with occlusion and few details. [ABSTRACT FROM AUTHOR]

High signal-to-noise ratio (SNR) seismic waveform data are conductive to various studies in seismology. Seismic denoising aims to enhance SNR by eliminating additive noise through signal processing while preserving important features of the seismic signal. Conventional parametric seismic denoising methods often require selecting appropriate parameters to achieve optimal results, which may be limiting when dealing with various types and scales of seismic data. Here, we develop an adaptive parameter-free denoising method by combining general cross-validation (GCV) thresholding and pixel connectivity in synchrosqueezed (SS) domain. In this denoising framework, the synchrosqueezed continuous wavelet transform (SS-CWT) is first applied to obtain a high-resolution time–frequency representation. Then, the GCV approach, which allows for choosing the (nearly) optimal threshold without relying on any prior knowledge about the noise level, is employed to attenuate most of the low-energy noise. After that, the relatively isolated high-energy residual noise remaining in the SS-CWT spectrum is removed using pixel connectivity thresholding. Finally, the inverse SS-CWT is applied to the thresholded spectrum to obtain the denoised seismic record. As the thresholds for GCV and pixel connectivity are derived from the spectrum characteristics of the data being analyzed, the proposed denoising approach is highly adaptive and parameter-free. We demonstrate the effectiveness and versatility of the proposed denoising framework using synthetic data and real seismic data from diverse monitoring scenarios, including land, ocean, and emerging distributed acoustic sensing (DAS). The results indicate that the method is a stable and efficient tool for seismic data denoising. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusion Magnetic resonance images (MRIs) are a valuable tool in the study of brain tumors, and multimodal sequences provide unique insights into different aspects of brain tumors. However, in clinical practice, missing modalities are often encountered due to various factors. This makes it difficult to obtain comprehensive and reliable information related to brain tumors.The purpose of this work is to develop an algorithm for the synthesis of missing MRI modality with high precision, and to center on generating accurate tumor‐related information to offer more data for clinical diagnosis.A novel weakly supervised MRI synthesis model named TAM‐DAM‐GAN has been proposed, which integrates tumor‐aware and detail adjustment mechanisms to enhance the quality of tumor generation. The tumor‐aware mechanism leverages weak label information to guide the network to classify images based on crucial information in local structures, thereby compelling the generative network to identify and highlight the learning of local tumor regions. The detail adjustment mechanism utilizes a discriminator to create attention maps at the pixel level in real‐time. These maps are then used to modify the loss weight, which in turn adjusts the details that are generated.Generation quality of four tasks (T1‐to‐T2, T2‐to‐T1, T1‐to‐FLAIR, and FLAIR‐to‐T1) was evaluated. Experiments on the BRATS2015 dataset show that the proposed approach is superior in both qualitative and quantitative measures. Taking FLAIR‐to‐T1 as an example, TAM‐DAM‐GAN improves PSNR of tumor region from 18.556 to 20.576 compared to baseline. Also, using real FLAIR data with generated T1 data boosts tumor segmentation accuracy by 10% compared to using only real FLAIR data.This finding will be conducive to enhancing the accuracy of cross‐modality synthesis in incomplete multimodal MRI, especially for tumor regions, thereby providing more dependable and comprehensive data for clinical diagnosis and scientific research. [ABSTRACT FROM AUTHOR]

This paper presents an efficient environment map sampling algorithm designed to render high‐quality, low‐noise images with only a few light samples, making it ideal for real‐time applications. We observe that bright pixels in the environment map produce high‐frequency shading effects, such as sharp shadows and shading, while the rest influence the overall tone of the scene. Building on this insight, our approach differs from existing techniques by categorizing the pixels in an environment map into emissive and non‐emissive regions and developing specialized algorithms tailored to the distinct properties of each region. By decomposing the environment lighting, we ensure that light sources are deposited on bright pixels, leading to more accurate shadows and specular highlights. Additionally, this strategy allows us to exploit the smoothness in the low‐frequency component by rendering a smaller image with more lights, thereby enhancing shading accuracy. Extensive experiments demonstrate that our method significantly reduces shadow artefacts and image noise compared to previous techniques, while also achieving lower numerical errors across a range of illumination types, particularly under limited sample conditions. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have great improvements for single image super resolution (SISR). However, most of the existing SISR pre-training models can only reconstruct low-resolution (LR) images in a single image, and their upsamling factors cannot be non-integers, which limits their application in practical scenarios. In this letter, we propose a multi-scale cross-fusion network (MCNet) to accomplish the super-resolution task of images at arbitrary scale. On the one hand, the designed scale-wise module (SWM) combine the scale information and pixel features to fullly improve the representation ability of arbitrary-scale images. On the other hand, we construct a multi-scale cross-fusion module (MSCF) to enrich spatial information and remove redundant noise, which uses deep feature maps of different sizes for interactive learning. A large number of experiments on four benchmark datasets show that the proposed method can obtain better super-resolution results than existing arbitrary scale methods in both quantitative evaluation and visual comparison. [ABSTRACT FROM AUTHOR]

Wearable haptics serve as an enhanced media to connect humans and VR/robots. The inevitable sweating issue in all wearables creates a bottleneck for wearable haptics, as the sweat/moisture accumulated in the skin/device interface can substantially affect feedback accuracy, comfortability, and create hygienic problems. Nowadays, wearable haptics typically gain performance at the cost of sacrificing the breathability, comfort, and biocompatibility. Here, we developed a fully integrated breathable haptic textile (FIBHT) to solve these trade-off issues, where the FIBHT exhibits high-level integration of 128 pixels over the palm, great stretchability of 400%, and superior permeability of over 657 g/m²/day (moisture) and 40 mm/s (air). It is a stand-alone haptic system totally composed of stretchable, breathable, and bioadhesive materials, which empowers it with precise, sweating/movement-insensitive and dynamic feedback, and makes FIBHT powerful for virtual touching in broad scenarios. [ABSTRACT FROM AUTHOR]

This study presents the spatial interactions downscaling (SPID) method and introduces the climate data for adaptation and vulnerability assessments (ClimAVA) dataset. SPID employs random forest models to capture the relationship between spatial patterns at global circulation model (GCM) resolution and fine-resolution pixel values. In summary, a random forest model is trained for each fine spatial resolution pixel of the reference data as the predictand, and nine pixels from the spatially resampled (coarser) version of the reference data at the GCM's resolutions as predictors. Models are then utilized to downscale the bias-corrected GCM data. The ClimAVA-SW dataset offers a high-resolution (4 km), bias-corrected, downscaled future climate projection derived from seventeen CMIP6 GCMs. It includes three variables (daily precipitation, minimum and maximum temperature) for three shared socioeconomic pathways (SSP245, SSP370, SSP585) across the U.S. Southwest region. The ClimAVA dataset sets itself apart with the SPID method's capacity to provide remarkable climate realism, high physical plausibility of change, and excellent representation of extreme events while maintaining user-friendliness and requiring relatively low computational resources. [ABSTRACT FROM AUTHOR]

Naked-eye 3D micro-LED display combines the characteristics of 3D display with the advantages of micro-LED. However, the 3D micro-LED display is still at the conceptual stage, limited by its intrinsic emission properties of large divergence angle and non-coherence, as well as difficulties in achieving large viewing angles with high luminous efficiency. In this work, we propose a double-layer metasurface film integrating functions of collimation with multiple deflections, constituting a micro-LED naked-eye 3D display system. The system is characterized through numerical simulations using the 3D finite-difference time-domain method. The simulation results show that the double-layer metasurface film restricts 90% of the emitted light of the micro-LED to the vicinity of the 0° angle, improving its spatial coherence. Subsequently, a large-angle, low-crosstalk outgoing from −45° to 45° is achieved, while providing a deflection efficiency of over 80% and a pixel density of up to 605. We believe this design provides a feasible approach for realizing naked-eye 3D micro-LED displays with a large field of view, low crosstalk, and high resolution. [ABSTRACT FROM AUTHOR]

In recent years, deep learning models have dramatically influenced image inpainting. However, many existing studies still suffer from over‐smoothed or blurred textures when missing regions are large or contain rich visual details. To restore textures at a fine‐grained level, a multi‐stage inpainting approach is proposed, which applies a series of partial inpainting modules as well as a progressive inpainting module to inpaint missing areas from their boundaries to the centre successively. Some improvements are made on the partial convolutions to reduce artifacts like blurriness, which require a convolution kernel to contain known pixels more than a certain proportion. Towards photorealistic inpainting results, the intermediate outputs from each stage are used to compute the loss. Finally, to facilitate the training process, a multi‐step training is designed that progressively adds inpainting modules to optimize the model. Experiments show that this method outperforms the current excellent techniques on the publicly available datasets: CelebA, Places2 and Paris StreetView. [ABSTRACT FROM AUTHOR]

A recent approach to image steganography is to use deep learning. Mainly, convolutional neural networks can extract complex features and use them as patterns to combine hidden messages and images. Also, by using generative adversarial networks, it is possible to generate realistic and high‐quality stego images without any noticeable artifacts. Previous methods suffered from challenges such as simple architecture, low network accuracy, imbalance between capacity and transparency, vanishing gradients, and low capacity. This study introduces a steganography framework named VidaGAN that utilizes deep learning techniques. The network being proposed is made up of three components: an encoder, a decoder, and a critic, and introduces a novel architecture and several innovations to address some of the unresolved challenges mentioned above. This study introduces a novel method for embedding any type of binary data into images using generative adversarial networks, enabling us to enhance the visual appeal of images generated by the specified model. This neural network called VarIable aDAptive GAN (VidaGAN) achieved state‐of‐the‐art status by reaching a hiding capacity of 3.9 bits per pixel in the DIV2K dataset. Furthermore, examination by the StegExpose steganalysis tool shows an AUC of 0.6, a suitable threshold for transparency. [ABSTRACT FROM AUTHOR]

A new image encryption algorithm based on the triple chaotic maps is proposed to deal with the issues of inadequate security and low encryption efficiency. Coloured images consist of three linked channels used in the scheme. This method uses different keys to break the correlations between adjacent pixels in each channel. The triple chaotic maps are Lorenz, 2D‐Logistic, and Henon. First, the plain image is split into RGB channels to encrypt each channel separately. Second, the triple chaotic maps generate two groups of keys. The first group of keys performs a pixel permutation, resulting in scrambled channels used as input for the following step. Finally, the second group of keys is used to diffuse the scrambled channels independently, resulting in diffused channels, which are then merged to obtain a cipher image. The triple chaotic maps of different orders generate the cipher image with great unpredictability and security. The security is evaluated using various measures. The results demonstrated a high level of security attained by successfully encrypting coloured images. Recent encryption algorithms are compared in terms of entropy, correlation coefficients, and attack robustness. The proposed method provided outstanding security and outperformed existing image encryption algorithms. [ABSTRACT FROM AUTHOR]

Semantic segmentation of underwater fish images is vital for monitoring fish stocks, assessing marine resources, and sustaining fisheries. To tackle challenges such as low segmentation accuracy, inadequate real‐time performance, and imprecise location segmentation in current methods, a novel lightweight U‐Net model is proposed. The proposed model acquires more segmentation details by applying a multiple‐input approach at the first four encoder levels. To achieve both lightweight and high accuracy, a multi‐scale residual structure (MRS) module is proposed to reduce parameters and compensate for the accuracy loss caused by the reduction of channels. To improve segmentation accuracy, a multi‐scale skip connection (MSC) structure is further proposed, and the convolution block attention mechanism (CBAM) is introduced at the end of each decoder level for weight adjustment. Experimental results demonstrate a notable reduction in model volume, parameters, and floating‐point operations by 94.20%, 94.39%, and 51.52% respectively, compared to the original model. The proposed model achieves a high mean intersection over union (mIOU) of 94.44%, mean pixel accuracy (mPA) of 97.03%, and a frame rate of 43.62 frames per second (FPS). With its high precision and minimal parameters, the model strikes a balance between accuracy and speed, making it particularly suitable for underwater image segmentation. [ABSTRACT FROM AUTHOR]

Bolt loosening detection is crucial for ensuring the safe operation of equipment. This paper presents a vision-based real-time detection method that identifies bolt loosening by recognizing anti-loosening line markers at bolt connections. The method employs the YOLOv10-S deep learning model for high-precision, real-time bolt detection, followed by a two-step Fast-SCNN image segmentation technique. This approach effectively isolates the bolt and nut regions, enabling accurate extraction of the anti-loosening line markers. Key intersection points are calculated using ellipse and line fitting techniques, and the loosening angle is determined through spatial projection transformation. The experimental results demonstrate that, for high-resolution images of 2048 × 1024 pixels, the proposed method achieves an average angle detection error of 1.145° with a detection speed of 32 FPS. Compared to traditional methods and other vision-based approaches, this method offers non-contact measurement, real-time detection capabilities, reduced detection error, and general adaptability to various bolt types and configurations, indicating significant application potential. [ABSTRACT FROM AUTHOR]

Digital image compression is applied to reduce camera bandwidth and storage requirements, but real-time lossless compression on a high-speed high-resolution camera is a challenging task. The article presents hardware implementation of a Bayer colour filter array lossless image compression algorithm on an FPGA-based camera. The compression algorithm reduces colour and spatial redundancy and employs Golomb–Rice entropy coding. A rule limiting the maximum code length is introduced for the edge cases. The proposed algorithm is based on integer operators for efficient hardware implementation. The algorithm is first verified as a C++ model and later implemented on AMD-Xilinx Zynq UltraScale+ device using VHDL. An effective tree-like pipeline structure is proposed to concatenate codes of compressed pixel data to generate a bitstream representing data of 16 parallel pixels. The proposed parallel compression achieves up to 56% reduction in image size for high-resolution images. Pipelined implementation without any state machine ensures operating frequencies up to 320 MHz. Parallelised operation on 16 pixels effectively increases data throughput to 40 Gbit/s while keeping the total memory requirements low due to real-time processing. [ABSTRACT FROM AUTHOR]

An event camera is a neuromimetic sensor inspired by the human retinal imaging principle, which has the advantages of high dynamic range, high temporal resolution, and low power consumption. Due to the interference of hardware and software and other factors, the event stream output from the event camera usually contains a large amount of noise, and traditional denoising algorithms cannot be applied to the event stream. To better deal with different kinds of noise and enhance the robustness of the denoising algorithm, based on the spatio-temporal distribution characteristics of effective events and noise, an event stream noise reduction and visualization algorithm is proposed. The event stream enters fine filtering after filtering the BA noise based on spatio-temporal density. The fine filtering performs time sequence analysis on the event pixels and the neighboring pixels to filter out hot noise. The proposed visualization algorithm adaptively overlaps the events of the previous frame according to the event density difference to obtain clear and coherent event frames. We conducted denoising and visualization experiments on real scenes and public datasets, respectively, and the experiments show that our algorithm is effective in filtering noise and obtaining clear and coherent event frames under different event stream densities and noise backgrounds. [ABSTRACT FROM AUTHOR]

A method for creating broadband ultrathin azo dye micropolarizers is introduced, utilizing photoalignment technology and liquid crystal polymers to organize azo dyes into a long-range ordered structure. Achievements include a 3.63 μm thick polarizer with an extinction ratio over 140 and polarization efficiency over 99.3% across 400–650 nm, 5 μm × 5 μm pixel pitch flexible ultrathin checkerboard arrays and 6 μm pixel pitch flexible ultrathin one-dimensional grating with a 0.45 duty ratio through mask exposure technology. After a substrate-transfer technique, the bending cycle test demonstrates the mechanical stability and durability of the broadband ultrathin flexible polarizers, highlighting their potential for widespread use in integrated flexible optoelectronic systems. [ABSTRACT FROM AUTHOR]

The risk of information leaks increases as images become a crucial medium for information sharing. There is a great need to further develop the versatility of image encryption technology to protect confidential and sensitive information. Herein, using high spatial redundancy (strong correlation of neighboring pixels) of the image and the in situ encryption function of a quantum dot functionalized encryption camera, in situ image encryption is achieved by designing quantum dot films (size, color, and full width at half maximum) to modify the correlation and reduce spatial redundancy of the captured image during encryption processing. The correlation coefficients of simulated encrypted image closely apporach to 0. High‐quality decrypted images are achieved with a PSNR of more than 35 dB by a convolutional neural network‐based algorithm that meets the resolution requirements of human visual perception. Compared with the traditional image encryption algorithms, chaotic image encryption algorithms and neural network‐based encryption algorithms described previously, it provides a universal, efficient and effective in situ image encryption method. [ABSTRACT FROM AUTHOR]

This paper presents a quantitative index introduced, ‘clarity,’ which can address both the ultrasound probe's brightness and full contact states to indicate ultrasound image quality for the robotic ultrasound system. Furthermore, it evaluates its performance through an experiment, a comparative analysis, and a questionnaire. The index is calculated based on pixel statistics within the predefined region of interest. Experimental validation is conducted by implementing a robotic ultrasound system and performing experiments using two phantoms. Notably, the Results demonstrate the distinction of the visible difference in ultrasound images but also show that it is hard to classify the tiny difference. Additionally, a questionnaire was carried out to ask about the recognition of good image quality. The opinions are the same trends and patterns. The 53.4 clarity value was determined from the answers as the boundary between good and bad-quality images. The experiment results, and questionnaire findings suggest that the proposed clarity index could be a reliable tool for evaluating ultrasound image quality in robotic systems, offering insights for improving diagnostic accuracy and efficiency. This research provides a clear framework for assessing ultrasound image quality in robotic applications, paving the way for advancements in the efficacy and precision of ultrasound imaging techniques. [ABSTRACT FROM AUTHOR]