Edge Extraction Research Articles

Mechanical condition diagnosis method of high‐voltage reactor using its oil tank operation deflection shape

AbstractAfter the long‐term operation, multiple mechanical defects (i.e. loosening of winding and core) of the high‐voltage reactor will emerge. Mechanical conditions of these critical components inside the high‐voltage reactors differ vibration of the oil tank. Thus, in this paper, array vibration sensors attached to the external surface of the tank are utilized to derive the operation deflection shape, which provides effective‐rich information for defects diagnosis. The influence of the applied voltage and mechanical conditions are deeply investigated, and the results indicate that the vibration of the frequency components at 100 Hz is only related to mechanical conditions but not sensitive to the applied voltage. Thereby, nodal lines are extracted from operation deflection shape at the same frequency (100 Hz) using edge extraction, which contains less interference information compared to the traditional greyscale image. The distance between nodal line features, estimated by the Siamese network, is adopted as an effective indicator to classify various defect types and levels of multiple mechanical conditions. Experimental results confirm the accuracy and feasibility of this proposed method in identifying mechanical conditions, and the respective identification accuracy for defects of winding and iron core reaches 100% and 92.9%, which is better than that from greyscale samples.

Remote Sensing Image Super-Resolution Using Texture Enhancing Generative Adversarial Network

<p>Single image super-resolution (SISR) brings excellent improvement in remote sensing applications, which has been widely studied in recent years. A method named TFSRGAN of remote sensing single image super-resolution based on generative adversarial network is proposed in this paper to address the problems of poor reconstruction visual quality and smooth details in traditional algorithms. In the proposed framework, s dense residual connection method is proposed to fuse the deep features from each residual block based on the SRGAN network, and the channel attention mechanism is added into the residual block to combinate the channel information. In addition, the network employs an edge extractor to divide the low-resolution image into low-frequency image and high-frequency image as the input of generator to improve the effect of texture reconstruction. Extensive comparison experiments were performed using AID, UCAS_AOD and China Gaofen-1 datasets, the SR results demonstrate that the proposed TFSRGAN framework outperforms the state-of-the-art algorithms including VDSR, SRGAN and ESRGAN in terms of objective evaluation metrics and subjective visual perception. The ground targets detection experiments represent that the proposed TFSRGAN can significantly improve the effect in remote sensing super-resolution application.</p> <p> </p>

A Technical Analysis of Digital Image and Video Processing

Video processing is the most emergent area of image processing in Research and Development. This paper, we present some advanced technology interrelated to video and image processing, which will provide a super-resolution high-quality most prominent visible light video for better human visualization and background motions or gesticulations of the human brain. There are two approaches for increasing the current resolution level of an image. The first one is the improvement of spatial resolution by reducing the size of pixels through the techniques of sensor manufacturing by about 40 M m 2 for a 0.35 M m CMOS process and the second approach is the enhancement of chip size that also enhances the capacitance. In video processing, we mainly focus on object images, i.e. any form of signal processing in which the input is an image and the output is a photograph or a frame of video. So, it will be better to converge over techniques of digital image processing. In the proposed algorithm (MHI Simulink model), edge extraction is performed to find the precious area of MRI and CT-Scan images. Using FPGA, edge detection methods have been implemented over scanned images to get better accuracy. The accuracy of the proposed method has been compared with Prewitt and Sobel’s edge detection techniques. The proposed method has given better accuracy than Prewitt and Sobel methods. Finally, this paper shows future directions for researchers to enhance the characteristics of digital image and video processing.

GDB: Gated Convolutions-based Document Binarization

Document binarization is a crucial pre-processing step for various document analysis tasks. However, existing methods fail to accurately capture stroke edges, primarily due to the inherent limitations of vanilla convolutions and the absence of adequate boundary-related supervision during stroke edge extraction. In this paper, we formulate text extraction as the learning of gating values and propose an end-to-end network architecture based on gated convolutions, named GDB, to address the problem of imprecise stroke edge extraction. The gated convolutions enable the selective extraction of stroke feature with different attention. Our proposed framework comprises two stages. Firstly, a coarse sub-network with an extra edge branch is trained to enhance the precision of feature maps by incorporating a priori mask and edge information. Secondly, a refinement sub-network is cascaded to enhance the output of the first stage using gated convolutions based on the sharp edges. To effectively incorporate global information, GDB also integrates a parallelized multi-scale operation that combines local and global features. We conduct comprehensive experiments on ten Document Image Binarization Contest (DIBCO) datasets from 2009 to 2019 and Document Deblurring Datasets. Experimental results show that our proposed methods outperform the state-of-the-art methods across all metrics on average. Extensive ablation studys demonstrate the efficacy of key components. Available codes: https://github.com/Royalvice/GDB.

PKDN: Prior Knowledge Distillation Network for bronchoscopy diagnosis

Bronchoscopy plays a crucial role in diagnosing and treating lung diseases. The deep learning-based diagnostic system for bronchoscopic images can assist physicians in accurately and efficiently diagnosing lung diseases, enabling patients to undergo timely pathological examinations and receive appropriate treatment. However, the existing diagnostic methods overlook the utilization of prior knowledge of medical images, and the limited feature extraction capability hinders precise focus on lesion regions, consequently affecting the overall diagnostic effectiveness. To address these challenges, this paper proposes a prior knowledge distillation network (PKDN) for identifying lung diseases through bronchoscopic images. The proposed method extracts color and edge features from lesion images using the prior knowledge guidance module, and subsequently enhances spatial and channel features by employing the dynamic spatial attention module and gated channel attention module, respectively. Finally, the extracted features undergo refinement and self-regulation through feature distillation. Furthermore, decoupled distillation is implemented to balance the importance of target and non-target class distillation, thereby enhancing the diagnostic performance of the network. The effectiveness of the proposed method is validated on the bronchoscopic dataset provided by Harbin Medical University Cancer Hospital, which consists of 2,029 bronchoscopic images from 200 patients. Experimental results demonstrate that the proposed method achieves an accuracy of 94.78% and an AUC of 98.17%, outperforming other methods significantly in diagnostic performance. These results indicate that the computer-aided diagnostic system based on PKDN provides satisfactory accuracy in diagnosing lung diseases during bronchoscopy.

An edge detail enhancement strategy based on Fourier single-pixel imaging

In this study, we propose an edge detection scheme based on Fourier single-pixel imaging, which extracts edges directly from the Fourier spectrum of the target object. The numerical simulations and experimental results show that the edges extracted by the proposed scheme have a better signal-to-noise ratio (SNR) than those extracted by the phase-shift sinusoidal pattern scheme. Furthermore, we investigate the effect of edge extraction in the case of undersampling and propose a plug-and-play edge detection algorithm to enhance the image. Our work combines Fourier single-pixel imaging with edge detection to extract the edges of a target object without imaging, providing a new idea for edge detection techniques.

RTV-SIFT: Harnessing Structure Information for Robust Optical and SAR Image Registration

Registration of optical and synthetic aperture radar (SAR) images is challenging because extracting located identically and unique features on both images are tricky. This paper proposes a novel optical and SAR image registration method based on relative total variation (RTV) and scale-invariant feature transform (SIFT), named RTV-SIFT, to extract feature points on the edges of structures and construct structural edge descriptors to improve the registration accuracy. First, a novel RTV-Harris feature point detection method by combining the RTV and the multiscale Harris algorithm is proposed to extract feature points on both images’ significant structures. This ensures a high repetition rate of the feature points. Second, the feature point descriptors are constructed on enhanced phase congruency edge (EPCE), which combines the Sobel operator and maximum moment of phase congruency (PC) to extract edges from structured images that enhance robustness to nonlinear intensity differences and speckle noise. Finally, after coarse registration, the position and orientation Euclidean distance (POED) between feature points is utilized to achieve fine feature point matching to improve the registration accuracy. The experimental results demonstrate the superiority of the proposed RTV-SIFT method in different scenes and image capture conditions, indicating its robustness and effectiveness in optical and SAR image registration.

Hyperspectral image classification Based on weakened Laplacian pyramid and guided filtering

ABSTRACT In recent years, methods of spatial-spectral feature extraction have been widely used in hyperspectral image (HSI) classification and have achieved good performance. However, the ways are often unable to distinguish effectively the boundary of the adjacent ground objects. Multi-scale feature fusion alleviates the problems to a certain extent, but in the case of limited samples, the previous methods often fail to achieve the desired effect. In this paper, we propose a multi-scale hyperspectral image classification method based on weakened Laplacian pyramid and guided filtering to nicely distinguish the boundary of the different ground objects. This structure first obtains multi-scale information by constructing a weakened Laplacian pyramid, and weakens the magnification of Gaussian blur in the upsampling process. While obtaining multi-scale images, it can not only retain enough image information to expand feature samples but also emphasize edge information in the edge extraction of the Laplacian pyramid. Then, the weakened Laplacian pyramid feature map is used as the guiding image of the guiding filter, which can better preserve the edge features and further improve the classification performance of HSI. Extensive experiments are carried out on four HSI data sets. The results show that our method is superior in classification accuracy and computational cost.

Face Super-Resolution via Joint Edge Information and Attention Aggregation Network

Face super-resolution (SR) is a specialized image super-resolution problem that is particularly relevant in various intelligent transportation scenes such as video surveillance and identification systems. Deep learning-steered solutions for face images often leverage facial priors (i.e., face parsing and landmark) to restore intricate facial components and have demonstrated promising performance. However, these methods typically rely on abundant manually labeled data and require lengthy training times. In this work, we introduce a meaningful approach called the Joint Edge Information and Attention Aggregation Network (JEANet) for the face SR problem. JEANet is established on our carefully designed Face Attention Aggregation Module (FAAM), which incorporates parallel connections of both channel-wise and spatial-wise features. Specifically, we integrate an attention fusion strategy into the residual blocks and elaborately employ edge blocks to extract edge information. Additionally, we introduce adaptive shortcuts that interpolate reconstruction parts at multiple scales. With the aid of adaptive shortcuts, JEANet effectively restores detailed images textures by leveraging contextual features optimally. These considerations enable the convolutional operations to flexibly distill information related to primary facial structures and progressively incorporate edge information to assemble local and global meaningful structures. Qualitative and quantitative evaluations demonstrate that our proposed method excels in recovering highly realistic face images compared to several competitive face SR methods.

Automatic infrared image distortion correction of electrolytic cells based on refined edge lines

Lens distortion greatly affects electrolysis fault location based on infrared images. This paper proposes a lens distortion correction method for the infrared images of electrolytic cell groups (ECGs) based on refined edge lines in a single ECG infrared image. Firstly, morphological operators are designed for ECG edge extraction, and the Hough transform method and an improved hierarchical method are combined to automatically separated the edge lines. Then, the least squares method is applied to refine the lines, and an optimization solution model is designed to calibrate the distortion parameters according to the refined lines. At last, an interpolation strategy is presented to restore pixel values of the corrected images with high speed and quality. The proposed method obtains a root mean squared error of the corrected lines of about 0.014 pixels, which is advanced and meets the fault location need. Moreover, high effectiveness is obtained with the proposed interpolation strategy.

Quantum Image Edge Extraction Algorithm for Noisy Image

Image preprocessing is important for noise exclusion in order to improve the accuracy of contour detection and image edge extraction. In this paper, a dual quantum spatial filter is proposed in order to reduce statistical noise, image blurring, impulsive noise, and retained details. Non-Maximum-Suppression and instead of manually operating threshold, adaptive thresholding operation is used in the quantum edge detection algorithm to detect more edge information with sharp edges. The circuit of the algorithm is realized through a series of operatives. We have compared PSNR, SSIM, precision rate, accuracy rate, recall rate, error rate, and computational complexity of the algorithm with operator based some existing classical and quantum edge extraction algorithms. The algorithm has the potential to get improved edge continuity, greater sharpness, and extract edge information having less proportion of noise.

A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM

This paper focuses on the problems of inaccurate extraction of winter wheat edges from high-resolution images, misclassification and omission due to intraclass differences as well as the large number of network parameters and long training time of existing classical semantic segmentation models. This paper proposes a lightweight winter wheat planting area extraction model that combines the DeepLabv3+ model and a dual-attention mechanism. The model uses the lightweight network MobileNetv2 to replace the backbone network Xception of DeepLabv3+ to reduce the number of parameters and improve the training speed. It also introduces the lightweight Convolutional Block Attention Module (CBAM) dual-attention mechanism to extract winter wheat feature information more accurately and efficiently. Finally, the model is used to complete the dataset creation, model training, winter wheat plantation extraction, and accuracy evaluation. The results show that the improved lightweight DeepLabv3+ model in this paper has high reliability in the recognition extraction of winter wheat, and its recognition results of OA, mPA, and mIoU reach 95.28%, 94.40%, and 89.79%, respectively, which are 1.52%, 1.51%, and 2.99% higher than those for the original DeepLabv3+ model. Meanwhile, the model’s recognition accuracy was much higher than that of the three classical semantic segmentation models of UNet, ResUNet and PSPNet. The improved lightweight DeepLabv3+ also has far fewer model parameters and training time than the other four models. The model has been tested in other regions, and the results show that it has good generalization ability. The model in general ensures the extraction accuracy while significantly reducing the number of parameters and satisfying the timeliness, which can achieve the fast and accurate extraction of winter wheat planting sites and has good application prospects.

Optimized GICP registration algorithm based on principal component analysis for point cloud edge extraction

For iterative closest point (ICP) algorithm, the initial position and the number of iterations are needed in registration. At the same time, the ICP algorithm is easy to fall into local convergence and convergence speed is slow. By constructing K-D tree to search neighborhood points and artificially set threshold, plane fitting is carried out, the on-time point cloud to be deployed is separated from the complex background, and statistical analysis is used to calculate the distance between the point cloud and the neighborhood point to quickly remove the invalid point cloud. The surface equation is set to calculate the tangent plane of point cloud normal vector and each normal vector, and the local coordinate system is constructed. The angle between adjacent vectors and the local coordinate system is calculated to determine the feature point set of edge contour. According to the covariance matrix of the feature points set, the principal feature component is obtained, the principal axis direction of the two sets of point clouds is found, and the rotation matrix and the displacement vector are obtained. Finally, GICP precise registration of point cloud is carried out according to initial pose parameters and rigid body transformation matrix obtained by maximum likelihood estimation method. The results show that the optimized algorithm can effectively avoid local convergence. Compared with the traditional ICP algorithm, when the algorithm achieves the same registration accuracy in the public dataset experiment, the registration speed is on average 44.82% faster and the overlap rate is on average 15.26% higher. In the real dataset experiment, the registration speed is on average 59.04% faster, the registration accuracy is on average 30.24% higher and the overlap rate is on average 10.61% higher. This shows that the optimization algorithm is superior to the traditional ICP algorithm in registration accuracy and convergence speed.

A color edge extraction method on color image

A color edge extraction method on color image

Insulator Crack Detection Using Soft Computing Techniques

The edge extraction technique in image processing was used to identify and classify micro-cracks on the composite insulator material in order to extract the shed's micro-cracks. The composite insulator has a significant impact on the operation and even power lines, so faults in the composite insulator must be identified. From the standpoint of image processing, the proposed approach for this project includes an image of a composite insulator, including micro-cracks. To extract the micro-crack on the insulator, first preprocess the image to extract the insulators after graying and edge-detecting. Image analysis refers to the process of altering the features of an image by executing various adjustments or alterations utilizing various functions. The Sobel operator, the Canny operator, the Prewitt operator, and the Laplace operator are all edge extraction operators that use this concept. Finally, images of composite insulators were extracted using different methodologies and compared, and the images were assessed using composite insulator features.

A dual-task region-boundary aware neural network for accurate pulmonary nodule segmentation

Recently, the performance of pulmonary nodule segmentation has improved fast because of the development of deep learning-based methods. However, existing CNN-based methods still don’t solve the two issues, leading to poor segmentation: (1) The information of small nodules lost in continuous down-sampling operation; (2) Discriminative features can’t be extracted from non-solid nodules because whose gray values are close to the surrounding environment. This study proposes a novel dual-task region-boundary aware deep convolutional neural network to solve the problems above. A hierarchical feature module is proposed to capture multi-scale information, improving small nodules' segmentation accuracy. Boundary guided module is introduced to extract edge features and predict nodule boundaries directly. In addition, a feature aggregation module is proposed to aggregate features at different levels. Besides, to better optimize the segment results and reduce overfitting, the region-boundary aware loss function is proposed. The method is trained and tested on the LIDC-IDRI dataset and the LUNA16 dataset, and the results demonstrate that our method is efficient. More importantly, our method is suitable for the segmentation of various nodules, especially small nodules, GGO nodules, and part-solid nodules.

Geochemical enrichment, speciation and mobilization of arsenic and antimony in black shales (southern China): Evidence from sequential fractionation and XANES spectroscopy

The high geogenic levels of trace metal(loid)s preserved within black shale can be released during natural weathering, causing global concern. Currently, the accumulation, speciation and potential mobilization of two highly toxic metal(loid)s, arsenic (As) and antimony (Sb), from black shale to soils remain unresolved, which hinders the evaluation of their potential risk to surrounding environments. Here, we demonstrate the geochemical enrichment, species transformation, and leaching behavior of As and Sb by applying weathering-induced alteration, sequential extraction and synchrotron-based X-ray absorption near edge spectroscopy (XANES) in the analysis of a range of black shale and weathered samples from two profiles collected from typical Cambrian sedimentary strata of the Pearl River Delta, southern China. The results showed significant accumulation of trace metal(loid)s, including As (43.8–458.0 mg/kg), Sb (7.2–34.5 mg/kg), Cu (8.8–451.0 mg/kg) and Ni (22.2–108.0 mg/kg), in the black shale and weathered products, and high enrichment factors for As (22.0–266.8) and Sb (1.2–6.4) were observed, consistent with the very high degrees of weathering (chemical index of alteration: 83–91). Arsenic in the shale was dominated by arsenate (46–85%), as identified using XANES, and this was resulted from extensive weathering, which facilitated the oxidation of arsenite and arsenopyrite species. Accordingly, significant decreases in sulfide-associated As and Sb were observed in highly weathered products. As a result, As and Sb were primarily in the immobilizable fractions associated with amorphous and well-crystallized Fe/Mn oxides, largely due to the increased formation of secondary Fe (oxyhydr)oxides, including goethite-like minerals, which mainly derived from the oxidative weathering of chlorite-like minerals. Nevertheless, high concentrations of As (<64 μg/L), Sb (14–70 μg/L), and Ni (3–92 μg/L) still leached from black shale samples exposed to synthetic acid rain in the 18-h batch leaching experiment. Our combined characterization results indicated that a small percentage of the high contents of geogenic As and Sb could potentially be released. However, soluble trace metal(loid)s in shale leachate could still endanger surrounding ecosystems, and continual monitoring during long-term natural weathering processes is merited for global black shale regions.

Automatic Identification of Thaw Slumps Based on Neural Network Methods and Thaw Slumping Susceptibility

Thaw slumping is a periglacial process that occurs on slopes in cold environments, where the ground becomes unstable and the surface slides downhill due to saturation with water during thawing. In this study, GaoFen-1 remote sensing and fused multi-source feature data were used to automatically map thaw slumping landforms in the Beilu River Basin of the Qinghai–Tibet Plateau. The bi-directional cascade network structure was used to extract edges at different scales, where an individual layer was supervised by labeled edges at its specific scale, rather than directly applying the same supervision to all convolutional neural network outputs. Additionally, we conducted a 5-year multi-scale feature analysis of small baseline subset interferometric synthetic aperture radar deformation, normalized difference vegetation index, and slope, among other features. Our study analyzed the performance and accuracy of three methods based on edge object supervised learning and three preconfigured neural networks, ResNet101, VGG16, and ResNet152. Through verification using site surveys and multi-data fusion results, we obtained the best ResNet101 model score of intersection over union of 0.85 (overall accuracy of 84.59%).The value of intersection over union of the VGG and ResNet152 are 0.569 and 0.773, respectively. This work provides a new insight for the potential feasibility of applying the designed edge detection method to map diverse thaw slumping landforms in larger areas with high-resolution images.

A conveyor belt characterization information extraction method based on YOLOv5 and the skeleton method

To resolve the inaccurate localization of conveyor belt surface damage identification problem and to address the insufficiencies of the methods for extracting surface characterization information, this paper proposes a conveyor belt characterization information extraction method that integrates YOLOv5 deep learning and the skeleton method. By constructing a conveyor belt surface damage recognition model based on the YOLOv5 target detection algorithm, the identification, localization and cropping of the conveyor belt’s surface damage are implemented. After that, edge extraction and surface information extraction are also performed on the damaged parts. Finally, the collected data are analyzed and processed in real time by edge computing equipment to determine the degree of damage of the parts. Finally, intelligent operation of the belt conveyor is achieved with autonomous operations, unattended operations and decision alarms. The experimental results show that the recognition accuracy of YOLOv5 is approximately 93.11%, the speed is approximately 57 frames per second and the error of the data acquired by image processing is between 2% and 10%, which meets the real-time detection requirements of conveyor belt surface damage detection, and assists in the safety management supervision of the belt conveyer.

Isotropic Two-Dimensional Differentiation Based on Dual Dynamic Volume Holograms

We study the use of two dynamic thick holograms to realize isotropic two-dimensional (2D) differentiation under Bragg diffraction. Acousto-optic modulators (AOMs) are used as dynamic volume holograms. Using a single volume hologram, we can accomplish a first-order derivative operation, corresponding to selective edge extraction of an image. Since the AOM is a 1D spatial light modulator, filtering of the image only occurs along the direction of the sound propagation. To achieve 2D image processing, two AOMs are used within a Mach–Zehnder interferometer (MZI). By aligning one AOM along the x-direction on the upper arm of the interferometer and another AOM along the y-direction on the lower arm, we accomplish the sum of two first-derivative operations, leading to isotropic edge extraction. We have performed both computer simulations and optical experiments to verify the proposed idea. The system provides additional operations in optical computing using AOMs as dynamic holograms.