Neighboring Pixels Research Articles

An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds

In transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes an autotuning hybrid method with Bayesian optimization for road edge extraction in highway systems. The hybrid method combines the strengths of 2D feature images and 3D spatial characteristics while also automatically tuning the hyperparameter combination using Bayesian optimization. The hyperparameters encompass high and low pixel gradient thresholds, neighborhood radius, and normal vector threshold. Later, the point cloud dataset of national highways in Henan Province, China, is taken as the case study to evaluate the performance of the proposed method against three benchmark methods in two typical road scenarios: straight and curved edges. Experimental results show that the proposed method outperforms the benchmarks in detection quality and accuracy. It can serve as a decision-making tool to complement traditional manual road surveying, enabling efficient and automated road edge extraction in highway systems.

A framework to model charge sharing and pulse pileup for virtual imaging trials of photon-counting CT

Objective.This study describes the development, validation, and integration of a detector response model that accounts for the combined effects of x-ray crosstalk, charge sharing, and pulse pileup in photon-counting detectors.Approach.The x-ray photon transport was simulated using Geant4, followed by analytical charge sharing simulation in MATLAB. The analytical simulation models charge clouds with Gaussian-distributed charge densities, which are projected on a 3×3 pixel neighborhood of interaction location to compute detected counts. For pulse pileup, a prior analytical method for redistribution of energy-binned counts was implemented for delta pulses. The x-ray photon transport and charge sharing components were validated using experimental data acquired on the CdTe-based Pixirad-1/Pixie-III detector using monoenergetic beams at 26, 33, 37, and 50 keV. The pulse pileup implementation was verified with a comparable Monte Carlo simulation. The model output without pulse pileup was used to generate spatio-energetic response matrices for efficient simulation of scanner-specific photon-counting CT (PCCT) images with DukeSim, with pulse pileup modeled as a post-processing step on simulated projections. For analysis, images for the Gammex multi-energy phantom and the XCAT chest phantom were simulated at 120 kV, both with and without pulse pileup for a range of doses (27-1344 mAs). The XCAT images were evaluated qualitatively at 120 mAs, while images for the Gammex phantom were evaluated quantitatively for all doses using measurements of attenuation coefficients and Calcium concentrations.Main results.Reasonable agreement was observed between simulated and experimental spectra with Mean Absolute Percentage Error Values (MAPE) between 10%and 31%across all incident energies and detector modes. The increased pulse pileup from increased dose affected attenuation coefficients and calcium concentrations, with an effect on calcium quantification as high as MAPE of 28%.Significance.The presented approach demonstrates the viability of the model for enabling VITs to assess and optimize the clinical performance of PCCT.

A quantum convolution and neighborhood pixel extraction scheme based on NEQR

A quantum convolution and neighborhood pixel extraction scheme based on NEQR

Event Stream Denoising Method Based on Spatio-Temporal Density and Time Sequence Analysis.

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.

An Image Encryption Algorithm Based on Tabu Search and Hyperchaos

In this paper, we propose a digital image encryption scheme based on Tabu Search (TS) algorithm and Chen’s hyperchaos system. First, in order to enhance the security of the algorithm and resist the known-plaintext attack, the key is associated with the ordinary image, and the hash value generated by the ordinary image is used as the initial value of the hyperchaotic system. Moreover, the TS algorithm is used to obtain the optimal subsequence to scramble the sub-block image, which ensures the scrambling effect of the algorithm. In addition, for the sake of minimizing the correlation of neighborhood pixels and strengthening the effect of scrambling, the ordinary image is divided into blocks for scrambling and diffusion. Through simulation and experiments, the key sensitivity, differential attack and pure ciphertext attack are analyzed. Compared with the other encryption schemes, the results verify the effectiveness and reliability of the proposed scheme.

Let It Snow: Intercomparison of Various Total and Snow Precipitation Data over the Tibetan Plateau

The Global Precipitation Measurement Mission (GPM) improved spaceborne precipitation data. The GPM dual-frequency precipitation radar (DPR) provides information on total precipitation (TP), snowfall precipitation (SF) and snowfall flags (surface snowfall flag (SSF) and phase near surface (PNS)), among other variables. Especially snowfall data were hardly validated. This study compares GPM DPR TP, SF and snowfall flags on the Tibetan Plateau (TiP) against TP and SF from six well-known model-based data sets used as ground truth: ERA 5, ERA 5 land, ERA Interim, MERRA 2, JRA 55 and HAR V2. The reanalysis data were checked for consistency. The results show overall high agreement in the cross-correlation with each other. The reanalysis data were compared to the GPM DPR snowfall flags, TP and SF. The intercomparison performs poorly for the GPM DPR snowfall flags (HSS = 0.06 for TP, HSS = 0.23 for SF), TP (HSS = 0.13) and SF (HSS = 0.31). Some studies proved temporal or spatial mismatches between spaceborne measurements and other data. We tested whether increasing the time lag of the reanalysis data (+/−three hours) or including the GPM DPR neighbor pixels (3 × 3 pixel window) improves the results. The intercomparison with the GPM DPR snowfall flags using the temporal adjustment improved the results significantly (HSS = 0.21 for TP, HSS = 0.41 for SF), whereas the spatial adjustment resulted only in small improvements (HSS = 0.12 for TP, HSS = 0.29 for SF). The intercomparison of the GPM DPR TP and SF was improved by temporal (HSS = 0.3 for TP, HSS = 0.48 for SF) and spatial adjustment (HSS = 0.35 for TP, HSS = 0.59 for SF).

A Hybrid Segmentation Algorithm for Rheumatoid Arthritis Diagnosis Using X-ray Images

Rheumatoid Arthritis (RA) is a chronic autoimmune illness that occurs in the joints, resulting in inflammation, pain, and stiffness. X-ray examination is one of the most common diagnostic procedures for RA, but manual X-ray image analysis has limitations because it is a time-consuming procedure and is prone to errors. A specific algorithm aims to a lay stable and accurate segmenting of carpal bones from hand bone images, which is vitally important for identifying rheumatoid arthritis. The algorithm demonstrates several stages, starting with Carpal bone Region of Interest (CROI) specification, dynamic thresholding, and Gray Level Co-occurrence Matrix (GLCM) application for texture analysis. To get the clear edges of the image, the component is first converted to the greyscale function and thresholding is carried out to separate the hand from the background. The pad region is identified to obtain the contours of it, and the CROI is defined by the bounding box of the largest contour. The threshold value used in the CROI method is given a dynamic feature that can separate the carpal bones from the surrounding tissue. Then the GLCM texture analysis is carried out, calculating the number of pixel neighbors, with the specific intensity and neighbor relations of the pixels. The resulting feature matrix is then employed to extract features such as contrast and energy, which are later used to categorize the images of the affected carpal bone into inflamed and normal. The proposed technique is tested on a rheumatoid arthritis image dataset, and the results show its contribution to diagnosis of the disease. The algorithm efficiently divides carpal bones and extracts the signature parameters that are critical for correct classification of the inflammation in the cartilage images.

Interval Type-2 enhanced possibilistic fuzzy C-means noisy image segmentation algorithm amalgamating weighted local information

The fuzzy clustering algorithms based on interval type-2 are effective methods for data clustering and image segmentation with some potential advantages in dealing with higher-order uncertainty. However, the fuzzy clustering algorithms based on interval type-2 have limited accuracy in noisy image segmentation. Therefore, we propose a new noisy image segmentation algorithm based on weighted local information for interval type-2 enhanced possibilistic fuzzy C-means clustering. Firstly, a new possibilistic fuzzy weighted local information factor, which amalgamates the mutually guided image filtering, is devised to control the relationship between mutually guided image filtering and the original image utilizing the absolute difference image between the original image and mutually guided image filtering. Additionally, two weighted sum functions are also introduced into the new possibilistic fuzzy weighted local information factor to calculate the grayscale differences between the current pixel and its neighborhood pixels. Secondly, the distance of the objective function is corrected using mutually guided image filtering to obtain the local features and global information of the image. Finally, this paper introduces the new possibilistic fuzzy weighted local information factor into the interval type-2 possibilistic fuzzy C-means and proposes a new interval type-2 enhanced possibilistic fuzzy C-means clustering algorithm with local information and mutually guided image filtering constraints to improve noisy image segmentation results. Through extensive experiments on noisy synthetic images and noisy real images, the proposed algorithm can achieve higher performance and more accurate segmentation results compared with several existing algorithms.

NeighborNet: Learning Intra- and Inter-Image Pixel Neighbor Representation for Breast Lesion Segmentation.

Breast lesion segmentation from ultrasound images is essential in computer-aided breast cancer diagnosis. To alleviate the problems of blurry lesion boundaries and irregular morphologies, common practices combine CNN and attention to integrate global and local information. However, previous methods use two independent modules to extract global and local features separately, such feature-wise inflexible integration ignores the semantic gap between them, resulting in representation redundancy/insufficiency and undesirable restrictions in clinic practices. Moreover, medical images are highly similar to each other due to the imaging methods and human tissues, but the captured global information by transformer-based methods in the medical domain is limited within images, the semantic relations and common knowledge across images are largely ignored. To alleviate the above problems, in the neighbor view, this paper develops a pixel neighbor representation learning method (NeighborNet) to flexibly integrate global and local context within and across images for lesion morphology and boundary modeling. Concretely, we design two neighbor layers to investigate two properties (i.e., number and distribution) of neighbors. The neighbor number for each pixel is not fixed but determined by itself. The neighbor distribution is extended from one image to all images in the datasets. With the two properties, for each pixel at each feature level, the proposed NeighborNet can evolve into the transformer or degenerate into the CNN for adaptive context representation learning to cope with the irregular lesion morphologies and blurry boundaries. The state-of-the-art performances on three ultrasound datasets prove the effectiveness of the proposed NeighborNet.

Contrast-based notch-to-crack transfer function for digital radiography

To simulate cracks, a series of slits with depths ranging from 17.2% to 40% of 301 stainless steel (SS) plate thickness are fabricated for this study. The examination includes a microfocus X-ray tube and a digital detector array (DDA) with 75 ??m pixel pitch. The basis of this study is to determine the effect of detector scintillator blur, noise and pixelation on the contrast of the resultant radiographic image and, ultimately, on the detectability of a crack. Many crack detectability studies are performed on notched plates rather than true cracks. As the notch width becomes smaller than a pixel, the grey value of the image it generates will be averaged over the entire footprint of the pixel. Therefore, the contrast with neighbouring (no notch) pixels is reduced. This study develops a relationship between the material property, detector parameters, notch geometry and expected contrast that would result from the radiograph image. This relationship can be used as a transfer function towards evaluating the resultant contrast from a notch and extrapolating the results towards a hairline crack.

Improved image denoising through fractional anisotropic diffusion and resolution-tailored differentiation in the Fourier domain

Fractional-order anisotropic diffusion-based denoising of images has been implemented in the literature through fractional differentiation in the Fourier domain. Furthermore, Fourier transform of the schemes on half-integer or integer mesh points has been used for the differentiation of images. In this paper, differentiation in the Fourier domain is proposed using schemes on fractional mesh points, aiming to enhance the performance of the algorithm. This can be regarded as employing fractional schemes at various resolutions, governed by a parameter of resolution within the range of (0.5, 1). Variations in resolution affect the pixel neighborhood by incorporating additional information from interpolated pixels. Experiments conducted on a reference image dataset, using three quantitative measures, demonstrate that the proposed method surpasses the method from the literature for higher values of the parameter of resolution. The improvement is particularly noticeable at higher noise levels, where the proposed method consistently outperforms the method from the literature across all values of the parameter of resolution. As a side effect, the proposed method is less time-consuming than the original method, as it requires higher time steps within the numerical scheme. Experiments and stability analysis show that the proposed method reduces the number of iterations by three to four times compared to the original method.

Learnable differencing center for nighttime depth perception

Depth completion is the task of recovering dense depth map from sparse ones, usually with the help of color images. Existing image guided methods perform well on daytime depth perception self-driving benchmarks, but struggle in nighttime scenarios with poor visibility and complex illumination. To address these challenges, we propose a simple yet effective learnable differencing center network (LDCNet). The key idea is to use recurrent inter-convolution differencing (RICD) and illumination affinitive intra-convolution differencing (IAICD) to enhance the nighttime color images and reduce the negative effects of the varying illumination, respectively. RICD explicitly estimates global illumination by differencing two convolutions with different kernels, treating the small-kernel-convolution feature as the center of the large-kernel-convolution feature in a new perspective. IAICD softly alleviates the local relative light intensity by differencing a single convolution, where the center is dynamically aggregated based on neighboring pixels and the estimated illumination map in the RICD. On both nighttime depth completion and depth estimation tasks, extensive experiments demonstrate the effectiveness of our LDCNet, reaching the state of the art.

Multi kernel cross sparse graph attention convolutional neural network for brain magnetic resonance imaging super-resolution

High-resolution Magnetic Resonance Imaging (MRI) is pivotal in both diagnosing and treating brain tumors, assisting physicians in diagnosis and treatment by displaying anatomical structures. Utilizing convolutional neural network-based super-resolution methods enables the efficient acquisition of high-resolution MRI images.However, Convolutional neural networks are limited by their kernel size, which restricts their ability to capture a wider field of view, potentially leading to feature omission and difficulties in establishing global and local feature relationships. To overcome these shortcomings, We have designed a novel network architecture that highlights three main modules: (i) Multiple Convolutional Feature (MCF)extraction module, which diversifies convolution operations for extracting image features, achieving comprehensive feature representation. (ii) Multiple Groupss of Cross-Iterative Feature(MGCIF) modules, promoting inter-channel feature interactions and emphasizing crucial features needed for subsequent learning. (iii) A Graph Neural Network Module based on a sparse attention mechanism, capable of connecting distant pixel features and identifying influential neighboring pixels for target pixel inpainting. To evaluate the accuracy of our proposed network, we conducted tests on four datasets, comprising two sets of brain tumor data and two sets of healthy head MRI data, all of which underwent varying degrees of degradation. We conducted experiments using nineteen super-resolution (SR) models. Our experiments were carried out on four datasets, and the results demonstrate that our method outperforms the current leading-edge methods. In the four datasets, our model showed improvements in Peak Signal-to-Noise Ratio (PSNR) scores compared to the second-place model,with increase of 1.16 %,1.08 %,0.19 % and 0.53 % for ×2,and 2.26 %,1.67 %,0.13 % and 0.45 % for × 4,respectively.

10‐3: Distinguished Paper: Reducing Resolution Loss in Naked Eye 3D Display Using Dual Ferroelectric Liquid Crystal (FLC) Shutters for Time‐multiplexed Light Field Display

Usually, the resolution loss is serious in light field display due to the spatial multiplexing of several neighboring pixels to display images from different directions. With the limitation in the resolution of the flat panel display, the light field 3D display shows insufficient display size, image depth, or resolution. This article utilized the FLC with a fast response at 2 kHz and the optimized charge compensation method to achieve a high refresh time multiplexing method, which can effectively increase the display resolution by up to 32 times and is very promising for light field 3D displays in the future.

VINCENT: Cyber-threat detection through vision transformers and knowledge distillation

Vision Transformers (ViTs) denote a family of attention-based deep learning techniques that have recently achieved amazing results in various problems related to the field of computer vision. In this paper, we explore the use of ViTs in problems of cyber-threat detection related to malware and network intrusion detection. In particular, we propose VINCENT, that is a novel deep neural method, which resorts to a color imagery representation of cyber-data by encoding related cyber-data features into neighboring color pixels. ViTs are trained from cyber-data images as teacher models, to extract explainable imagery signatures of cyber-data classes. This knowledge is extracted by leveraging the self-attention mechanism to give paired attention values between pairs of imagery patches. The signature knowledge, extracted through the ViT teacher, is, finally, used to train a smaller neural student model according to the knowledge distillation theory. Experiments with various benchmark cybersecurity datasets assess the accuracy of the student model VINCENT also compared to that of several state-of-the-art methods. In addition, it shows that VINCENT can obtain insights from explanations recovered through the self-attention mechanism of the ViT teacher.

Fine-Grained Multi-class Road Segmentation using MultiScale Probability Learning

Abstract: Driven road segmentation, a crucial part of advanced driver assistance systems, looks at the surroundings to keep vehicles within safe driving limits (ADASs). It begins by outlining the automatic lane detection shortfalls of conventional computer vision systems, pointing out problems such subpar segmentation, insufficient mask edge contours, sluggish processing, and restricted flexibility in intricate urban environments. Next, a multi-step procedure using deep learning networks is offered as a solution. This involves extracting vector skeletons, computing neighbouring pixels, assigning proportional weights depending on endpoints, and getting binary prediction masks. The conversation also touches on how self-driving technology will affect society, emphasizing how it could provide safe and intelligent transportation choices in the face of an increase in traffic accidents caused by careless drivers. Self-driving cars could be the first practical example of socially conscious robots interacting with humans, the story implies, even if it acknowledges possible public opposition. Furthermore, the story highlights the latest developments in autonomous driving technology, highlighting the vital requirement for strong sensing, perception, and cognitive technologies to enable completely autonomous vehicles that can adjust to changing road conditions.

Dual-complexities based on straightforward neighborhood pixel prediction in pixel-value-ordering framework for reversible data hiding

PVO-based schemes are the widely-used reversible data hiding (RDH) techniques. Benefiting from the good prediction performance, the stego-image can have a high quality. However, the complexity metric of PVO is still not good enough. The two main limitations are: the block-based context pixels are not highly correlated with the predicted pixel, and the fluctuation-based complexity calculation methods cannot comprehensively represent the real prediction result. Unlike the existing complexity metrics, we consider this problem from a novel viewpoint of neighborhood pixel prediction (NPP), i.e., using the prediction pixel to predict the unmodified neighborhood pixels of a predicted pixel. The neighborhood pixels are more reliable than the context pixels and the generated neighborhood prediction-errors (NPEs) are utilized to represent the real prediction-error (RPE). Two new features are extracted from NPEs as Dual-complexities to determine the embedding order. Experimental results indicate the quality of the stego-image can be improved significantly by using our proposed Dual-complexities in the related PVO-based schemes, and it can be directly extended to other schemes in PVO framework as well.

A novel space–spectrum array tile probability random-forest model enhances LULC mapping accuracy on Google Earth Engine: An experiment in Ordos, China

The rapid renewal of land use and land cover (LULC) maps using remote-sensing technologies constitutes a sine qua non for judicious land resource management at both regional and national scales. Existing research conducted on the Google Earth Engine (GEE) platform has overwhelmingly focused on pixel-based LULC classification techniques, often neglecting the role of spatial context via neighbouring valuable pixel information. Remarkably, little attention has been paid to the amalgamation of 3 × 3 neighbouring pixels into a three-dimensional space–spectrum array that can emulate the functionalities of object-based image analysis. In this study, we developed a novel integrated model consisting of a space–spectrum array (SSA) model based on 3 × 3 neighbouring pixels, a tile model based on random forest, and a multiple probabilistic classification model (SSA-TPRF) on the GEE platform to generate a LULC map with high overall accuracy (OA) for Ordos in 2020. Three bimonthly median value images were synthesised and feature collections, including spectral bands and vegetation indices, were constructed. Five experimental groups (EXP1–EXP5) were used to assess the different model combinations. Subsequent validation procedures employed abundant reference samples and compared the results with those of the three extant LULC mapping products. The results showed that EXP2, which was grounded in the tile-based model, yielded an OA of 87.53%, surpassing that of EXP1 (84.99%), which employed a traditional overall model. Furthermore, EXP3, which integrated the multiple probabilistic classification model with the traditional overall model, exhibited an OA of 85.19%, exceeding that of EXP1. A comparison of the five experimental groups using the four regional spatial subtlety features revealed that the EXP5, employing the SSA-TPRF model, successfully decreased the salt and pepper noise. The OA of six tile sizes ranging from 10 km to 100 km were compared, and the highest OA (88.35%) was achieved at a tile size of 25 km. The resultant LULC map in Ordos, derived from the SSA-TPRF model, showed superior OA compared with the extant LULC products. This study thus contributes to a versatile and scalable model within the GEE framework, offering avenues for facile adaptation and recurrent application across disparate geographical locations and temporal settings. The adaptability of this model is particularly advantageous for developing nations and regions typified by diverse landscapes, thereby catalysing the iterative updating of LULC maps through advanced remote-sensing paradigms.

Token singularity understanding and removal for transformers

This work delves into unveiling the singularity issue latent in global attention-based Transformers. Empirical and theoretical analyses elucidate that interrelationships among token channels lead to singularities, impeding the training of attention weights. Concretely, the similar neighbor pixels within image patches can form intercorrelated channels after being flattened. Images that one color dominates can possess correlated channels. Furthermore, the fixed global connection architecture retains correlation relationships, contributing to the persistence of singularities. High singularity risks reducing Transformers’ performance and robustness. Based on the singularity analysis, we propose the Token Singularity Removal (TSR) strategy. It incorporates the Dual-Tree Complex Wavelet Transform (DTCWT) stem and Feature Decorrelation (FD) loss, aiming to encourage Transformers to learn tokens with unrelated channels and eliminate singularities. Experimental validation across various image classification datasets and corruption image data sets demonstrate improved accuracy and robustness of Transformers utilizing the TSR strategy. Our code is publicly available at https://github.com/wdanc/TSR.

An efficient decision support system for leukemia identification utilizing nature-inspired deep feature optimization.

In the field of medicine, decision support systems play a crucial role by harnessing cutting-edge technology and data analysis to assist doctors in disease diagnosis and treatment. Leukemia is a malignancy that emerges from the uncontrolled growth of immature white blood cells within the human body. An accurate and prompt diagnosis of leukemia is desired due to its swift progression to distant parts of the body. Acute lymphoblastic leukemia (ALL) is an aggressive type of leukemia that affects both children and adults. Computer vision-based identification of leukemia is challenging due to structural irregularities and morphological similarities of blood entities. Deep neural networks have shown promise in extracting valuable information from image datasets, but they have high computational costs due to their extensive feature sets. This work presents an efficient pipeline for binary and subtype classification of acute lymphoblastic leukemia. The proposed method first unveils a novel neighborhood pixel transformation method using differential evolution to improve the clarity and discriminability of blood cell images for better analysis. Next, a hybrid feature extraction approach is presented leveraging transfer learning from selected deep neural network models, InceptionV3 and DenseNet201, to extract comprehensive feature sets. To optimize feature selection, a customized binary Grey Wolf Algorithm is utilized, achieving an impressive 80% reduction in feature size while preserving key discriminative information. These optimized features subsequently empower multiple classifiers, potentially capturing diverse perspectives and amplifying classification accuracy. The proposed pipeline is validated on publicly available standard datasets of ALL images. For binary classification, the best average accuracy of 98.1% is achieved with 98.1% sensitivity and 98% precision. For ALL subtype classifications, the best accuracy of 98.14% was attained with 78.5% sensitivity and 98% precision. The proposed feature selection method shows a better convergence behavior as compared to classical population-based meta-heuristics. The suggested solution also demonstrates comparable or better performance in comparison to several existing techniques.