Edge Detection Method Research Articles

Research on Image Processing and Edge Detection Methods for Ice-covered Cables and Ropes

Research on Image Processing and Edge Detection Methods for Ice-covered Cables and Ropes

Carpet Back Sizing Quality Assessment by Measuring the Amount of Resin Using Image Processing and Machine Learning Approaches

The mechanical properties of the carpet, such as dimensional stability, bending stiffness, handle and creeping on the surface during use, have a direct relationship with the amount of resin applied to the back of the carpet in the sizing process. In today’s factories, the optimal amount of resin and the mechanical quality of the carpet are controlled by the operator touching the carpet on the machine carpet finishing line or manually while rolling the carpet. Proposed in this paper is an automatic method based on the evaluation of the bending stiffness of the sized carpet that uses digital image processing and machine learning to measure the optimal amount of size concentration and control this index. For this purpose, during the final stage of carpet production, the carpet is folded in the middle, and two edges of the carpet are placed on top of each other. A side view image is then taken of the carpet. Using edge detection methods, the edges of the carpet are identified, and different features, such as the average, maximum and minimum statistics for the curve and contour angles, are then extracted. Different conventional machine learning approaches, such as KNN, CART and SVM, are applied. To evaluate the proposed method, a dataset containing 220 different images is used in a 10-fold cross-validation scheme. Different performance measures resulting from the evaluations demonstrate the effectiveness and applicability of the method.

Stable first-arrival picking through mathematical morphology and edge detection

SUMMARY First-arrival picking is a fundamental and challenging task in seismic data processing. Existing algorithms such as the cross-correlation algorithm (CCT) struggle to achieve satisfactory noise immunity while maintaining picking efficiency. In this paper, we propose the first-arrival picking through mathematical morphology and edge detection (FPME) algorithm with three steps. The converting step transforms the original data into a binary image though a filtering technique, where the binary image represents the global energy distribution of high-energy and low-energy samples. The rendering step delimits the signal zone in the binary image through morphological operations, where the signal zone eliminates the noise in the upper part. The picking step detects first arrivals in the signal zone through the edge detection methods, where an evaluation function is designed to select the optimal detection results as first arrivals. Experiments were performed on four field data sets. The results demonstrated that FPME is more stable and reliable than five classic and popular algorithms.

Seasonal potential fishing zone model in the regional fisheries management of Indonesia (WPP-RI) 716 based on remote sensing satellite data

The variability of atmosphere-ocean interactions highly influences the distribution of fishing zones in the surrounding Indonesia Through Flow (ITF) channel, such as the WPP-716 region. Therefore, the seasonal determination of the fishing zone is crucial in this zone as one of the regional fisheries managements in Indonesia. This study aims to create a potential fishing zone (PFZ) model in the Regional Fisheries Management of Indonesia (WPP-RI) 716 based on the remote sensing satellite data. This study used the daily SST data extracted from the Suomi-National Polar-Orbiting Partnership-Visible Infrared Imaging Radiometer Suite (SNPP-VIIRS) image Level 2 from 2018 to 2019. A Single Image Edge Detection (SIED) method is applied to determine the PFZ points. Supporting data, such as sea current patterns, chlorophyll-a, fish-catching zones and Catch per Unit of Effort (CpUE), are also considered to bolster this study's findings. The models were validated and compared with the results established by central authority fish catch data. Of particular concern, the highest detection of PFZ is observed during the second transitional season, reaching 1835 points scattered all over the study area. The frequently detected PFZ is identified in northern Sulawesi and Sangihe Islands, where the circular eddy current observed during the second transitional season, ranging from 0.6 to 0.8 m/s, indicating upwelling (high productivity) events proven by the variability of surface temperature and chlorophyll-a and aligned with the high value of CpUE (ranging from 20 to 28 ​kg/GT/day). The developed model is expected to be a basis for further decision-making regarding fishery resources management in the study area.

Digital Image Processing On Kaffir Orange Peel With Canny Edge Detection Algorithm

Object tracking is a form of application of computer vision. To be able to track an object, a stage is needed in the image processing process. Image Processing is a field related to the process of image transformation (image). The image processing process is carried out to obtain better image quality. The harvesting system in kaffir lime is done manually, by choosing fruits whose skin color is green, and not yellowish. Due to the small and asymmetrical size and shape of kaffir lime, manual harvesting systems are still widely used to maintain the quality and quantity of the harvest. In addition, the manual harvesting system can also avoid damage to kaffir lime trees and obtain optimally ripe kaffir limes. Kaffir lime also has genders like humans, namely males and females. In male kaffir lime there is a circle that is more prominent in size underneath, while female kaffir lime has a flat shape. However, for consumption and medicinal purposes both male and female kaffir lime can be used without affecting the taste or quality of the fruit. With the image processing to determine the level of wrinkles on quality kaffir lime peel, kaffir lime will be selected which is usually used for herbal medicines. In this case, the Canny Edge Detection algorithm can be used to identify density edges in kaffir lime peels. Thus, the degree of wrinkles in kaffir lime peel can be calculated and measured to be more accurate. And can be separated quality or non-quality kaffir lime with the image of kaffir lime that has been seen through the image. The results obtained in designing and analyzing the quality of kaffir lime are clearer and more accurate with an image resolution value of 248 x 216 that the orange is included in the female kaffir lime type.The results tested that the right edge detection method in carrying out the edge detection process in the image of kaffir lime peel is the Canny Edge Detection Algorithm. By using the image on the Canny Edge Detection Algorithm, more dense and quality kaffir lime results are obtained so that it can be used for herbal medicine.

Classification Algorithm of 3D Pattern Film Using the Optimal Widths of a Histogram

A recent development in marketing tools aimed at boosting sales involves the use of three-dimensional pattern films. These films are designed to captivate customers’ interest by applying 3D patterns to the surface of products. However, ensuring the quality of these produced 3D films can be quite challenging due to factors such as low contrast and unclear layout. Furthermore, there has been a shortage of research on methods for evaluating the quality of 3D pattern films, and existing approaches have often failed to yield satisfactory results. To address this pressing issue, we propose an algorithm for classifying 3D pattern films into either ‘good’ or ‘bad’ categories. Unlike conventional segmentation algorithm or edge detection methods, our proposed algorithm leverages the width information at specific heights of the image histograms. The experimental results demonstrate a significant disparity in histogram shapes between good and bad patterns. Specifically, by comparing the widths of all images at the quintile of the histogram height, we show that it is possible to achieve a 100% accuracy in classifying patterns as either ‘good’ or ‘bad’. In comparative experiments, our proposed algorithm consistently outperformed other methods, achieving the highest classification accuracy.

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.

COMPARISON OF EDGE DETECTION METHODS USING ROBERTS AND LAPLACIAN OPERATORS ON MANGO LEAF OBJECTS

Edge detection is a technique to find the outlines of an object in an image by detecting significant changes in brightness or discontinuities. This study discusses the comparison of edge detection using Roberts operators and Laplacian operators. The object used in edge detection is four types of mango leaves (Golek, Arum Manis, Madu, and Kuweni) with the *.jpeg format that has been pre-processed with 1000 x 278 pixels. The test used in this study compared the results of White Pixel values, MSE, and PSNR with test data as many as 24 data samples from four types of mango leaves. The results of the comparison of edge detection methods using the Laplacian operator get the lowest MSE value of 7.8577, the highest PSNR value of 39.2119, and the white pixel value of 164951, while the Roberts operator gets the lowest MSE value of 8.9723, the highest PSNR value of 38.6358, and the white pixel value of 155889.

A Fully Automatic DEXP Method for Gravity Data and Its Application on a Potash Salt Deposit

We developed an improved depth of extreme point (DEXP) method, characterized as an effective and rapid imaging method that can estimate the depth and distribution of a source quickly. Its main purpose is to solve various challenges. The automatic calculation aspect of the traditional method is often limited; namely, there is a problem with achieving automatic and reliable processing when the observed surface presents undulating topography, and this problem cannot be ignored. Therefore, we propose the addition of the constant method and the hypothetical observed surface method to achieve improvements in the traditional method. Firstly, we test the improved method on the synthetic models to demonstrate its notable advantage: the achievement of a fully automatic calculation without requiring any other additional information such as structural index (SI) values and threshold values. Meanwhile, we also demonstrate its ability and reliability to handle undulating topography with acceptable accuracy for imaging results. Furthermore, we verify the robustness of the improved method by applying it to real gravity data from the potash salt deposit in the Sakhon Nakhon basin, Laos. In this case, the improved DEXP method effectively identified the location of the potash deposit. Moreover, combined with the optimal edge detection method, gravity prospecting for potash salt deposits exhibited significant advantages.

FPGA-Based Improved Sobel Operator Edge Detection

Image edge detection is an important field in image processing, with its primary goal being to identify edge information of various objects in images. Traditional edge detection programs are mostly executed serially, resulting in low detection efficiency. This paper proposes an FPGA-based improved Sobel operator edge detection method, harnessing the parallel processing capability of FPGA to enhance detection efficiency. Building upon the Sobel operator in edge detection algorithms, this method increases the convolution calculation dimensions of the Sobel operator, expanding it from 2 directions to 8 directions for more precise edge information. Images captured by OV5640 are processed within the FPGA and displayed via VGA. Compared to other edge detection algorithms, the FPGA-based improved Sobel operator edge detection method efficiently and rapidly detects image edges, ensuring stable image display and accurate edge information.

Bio-inspired XYW parallel pathway edge detection network

Edge detection is of critical importance for middle-level and high-level tasks in computer vision. Existing edge detection methods usually use VGG16 as the encoding network and achieve exceptional performance through transfer learning, which has the characteristics of high parameters and high computational cost. Researchers have implemented edge detection by designing decoding networks. Unlike existing methods, this paper is inspired by the effective mechanisms of edge detection in the parallel pathway of biological vision and proposes a new lightweight encoding–decoding structure for edge detection networks, which we refer to as XYW-Net. In the encoding network, we drew inspiration from the receptive field properties of X-type cells, Y-type cells, and W-type cells involved in the parallel pathway, and developed more meticulous convolutional models. Based on the structure of the parallel pathway, the three cell modules are combined into a novel encoding network and excellent feature extraction performance is obtained. Within the decoding network, this paper draws inspiration from the feature integration ability of the inferotemporal cortex (IT) and introduces a novel feature integration module to constitute the decoding network. Experiments show that the proposed network in this paper obtains the Optimal Dataset Scale (ODS) = 0.812 on the BSDS500 dataset with only 0.79 M parameters. Additionally, the model has exhibited outstanding ODS performance on various publicly available edge detection datasets, including NYUD, BIPEDv1, and Multicue. Moreover, future research could concentrate on implementing more efficient antagonistic mechanisms and devising networks grounded in higher-level visual cortical mechanisms. This could further augment the performance and efficiency of edge detection networks. We encourage researchers to delve into these directions within the field. The codes are available at https://github.com/PXinTao/XYW-Net.

Application of Multiple-Optimization Filtering Algorithm in Remote Sensing Image Denoising.

Denoising remote sensing images is crucial in the application and research of remote sensing imagery. Noise in remote sensing images originates from sensor characteristics, signal transmission, and environmental conditions, among which Gaussian noise is the most common type. In this paper, we proposed a multiple-optimization bilateral filtering (MOBF) algorithm based on edge detection and differential evolution (DE) methods. The proposed algorithm optimizes the spatial domain filtering kernel and the spatial domain Gaussian kernel by using the standard deviation and width of the edge response. By employing the DE algorithm, the individuals in the population based on the standard deviation of the gray value domain are subjected to iterative mutation, crossover, and selection operations to refine the latent solution vectors and determine the optimal color space for optimizing the standard deviation of the pixel range domain kernel. As a result, the MOBF algorithm, which does not require any parameter input, is realized. To verify the feasibility and effectiveness of the proposed algorithm, denoising experiments were conducted on remote sensing images by using evaluation metrics such as the mean squared error, peak signal-to-noise ratio, and structural similarity index. The experimental results revealed that the MOBF algorithm outperforms traditional algorithms for all three evaluation metrics.

Video Motion Magnification and Subpixel Edge Detection-Based Full-Field Dynamic Displacement Measurement

Noncontact measurement techniques in structural dynamics field have progressed significantly in the past few decades. Vision-based measurement techniques are unique in that they have the ability to achieve full-field measurement and possess the typical advantages associated with noncontact measurement techniques. Recently, vision-based techniques have also been applied to streaming of videos for structural dynamic displacement measurement. The most recent trends in vision-based measurements include target tracing, digital image correlation, and target-less approaches. There are, however, some shortcomings of the vision-based techniques such as susceptibilities to image noise, prevailing light conditions, and limit in measurement resolution. To reduce these shortcomings, a method known as video motion magnification (MM) can be used to amplify small structural motions. Using the phase-based motion magnification (PBMM) and subpixel edge detection methods, the full-field dynamic displacements of the structure can be obtained. The deep convolutional long short-term memory (ConvLSTM) network is applied to aid in the selection of the frequency band for magnification in the PBMM algorithm. To achieve higher measurement accuracy, the displacement results with and without MM are combined with the finite impulse response (FIR) filter which can reduce the error caused by the PBMM procedure. In the tests, plastic optical fiber (POF) displacement sensors are introduced and used as reference measurements to compare the dynamic displacement results from the proposed vision-based method. Compared with the measured displacements with POF sensors, the proposed method offers high level of accuracy for full-field displacement measurement.

BUILDING EDGE DETECTION FROM VERY HIGH-RESOLUTION REMOTE SENSING IMAGERY USING DEEP LEARNING

Abstract. Detection of Building edges is crucial for building information extraction and description. Extracting structures from large-scale aerial images has been utilized for years in cartography. With commercially available high-resolution satellites, many aerial photography usages can now employ satellite imagery. Edge detection is focused on pinpointing distinct transitions between greyscale image regions and attributing their origins to underlying physical processes. Detecting building boundaries from very high-resolution (VHR) remote sensing data is essential for many geo-related applications, such as urban planning and management, surveying and mapping, 3D reconstruction, motion recognition, image registration, image enhancement and restoration, image compression, and more. The rapid evolution of convolutional neural networks (CNNs) has led to substantial breakthroughs in edge detection in recent years. Sharp, localized changes in brightness characterize edges in digital images. In most cases, edge detection requires some kind of image smoothing and separation. Differentiation is an ill-conditioned problem, and smoothing leads to information loss. It is challenging to create an edge detection method that works everywhere and adapts to any future processing stages. Therefore, throughout the development of digital image processing, numerous edge detectors have been created, each with its own unique set of mathematical and algorithmic properties. Several edge detectors have been developed due to application needs and the subjective nature of edge definition and characterization. We propose a deep learning technique, particularly convolutional neural networks(CNNs), that offers a promising approach to automatically learn and extract features from very high-resolution remote sensing imagery, leading to more accurate and efficient building edge detection.

Probing the Foreshock Wave Boundary With Single Spacecraft Techniques

AbstractIn space physics, wave measurements typically use a small number of datapoints due to limited available spacecraft. Common single‐spacecraft wave vector analysis techniques built around these limitations are widely used, even in regions where the wave amplitude profile may have a strong spatial dependence. We show that in these gradient regions, the divergence‐free condition of the magnetic field requires a local modification to the plane of polarization that is incorrectly interpreted by single‐spacecraft techniques. We explore the consequences of this result in the Earth's ion foreshock using both Acceleration, Reconnection, Turbulence, and Electrodynamics of the Moon’s Interaction with the Sun spacecraft data and a 2.5‐D hybrid Vlasov simulation conducted using the Vlasiator code. The observed foreshock ultralow frequency waves have a finite extent in the direction perpendicular to the Interplanetary Magnetic Field, and incorrect application of standard minimum variance techniques at the boundary yields a false wave vector orientation that may be used as a novel edge detection method. This method may be particularly useful for analysis of the ion foreshock at other planets where only a single spacecraft is available. More broadly, our results stand as a cautionary tale for wave analysis in other space physics contexts where the wave geometry is less clear.

Full-period fringe order correction method based on dual-threshold cellular automaton

In traditional temporal phase unwrapping (TPU) methods, the fringe order is obtained pixel-to-pixel by multi-frequencies or multi-wavelengths. The direct calculation and error non-accumulation features accelerate the prosperity of TPU. Nevertheless, the noise, defocusing, and non-uniform reflectivity may inevitably lead to some fringe order errors. These errors are powerless against the evolving TPUs such as Gray code and phase coding. In this paper, a full-period fringe order correction method based on dual-threshold cellular automaton is proposed for machine 3D vision. Initially, an advanced dual-threshold cellular automaton algorithm is employed to extract both the strong and weak edges of the wrapped phase individually. Superior to conventional single-threshold edge detection methods, this approach effectively mitigates the edge breakage problem caused by significant height variations. Subsequently, the N-filled map, N-residue mask, and N-start points concepts are introduced to sequentially segment independent connected domains based on the tightly graphical coupling. In addition, by performing edge compensation in the same period, accurate fringe order correction can be achieved even if excessive edge points are identified, as long as the broken edges are effectively connected. The experimental results exhibit exceptional correction performance of the proposed method for intricate isolated objects, objects with non-uniform reflectivity, and dynamic scenes.

A Fast Gradient Iterative Affine Motion Estimation Algorithm Based on Edge Detection for Versatile Video Coding

In the Versatile Video Coding (VVC) standard, affine motion models have been applied to enhance the resolution of complex motion patterns. However, due to the high computational complexity involved in affine motion estimation, real-time video processing applications face significant challenges. This paper focuses on optimizing affine motion estimation algorithms in the VVC environment and proposes a fast gradient iterative algorithm based on edge detection for efficient computation. Firstly, we establish judging conditions during the construction of affine motion candidate lists to streamline the redundant judging process. Secondly, we employ the Canny edge detection method for gradient assessment in the affine motion estimation process, thereby enhancing the iteration speed of affine motion vectors. The experimentalresults show that the encoding time of the affine motion estimation algorithm is about 15–35% lower than the overall encoding time of the anchor algorithm encoder, the average encoding time of the affine motion estimation part of the inter-frame prediction part is reduced by 24.79%, and the peak signal-to-noise ratio (PSNR) is only reduced by 0.04.

A Novel Gradient-Weighted Voting Approach for Classical and Fuzzy Circular Hough Transforms and Their Application in Medical Image Analysis—Case Study: Colonoscopy

Classical circular Hough transform was proven to be effective for some types of colorectal polyps. However, the polyps are very rarely perfectly circular, so some tolerance is needed, that can be ensured by applying fuzzy Hough transform instead of the classical one. In addition, the edge detection method, which is used as a preprocessing step of the Hough transforms, was changed from the generally used Canny method to Prewitt that detects fewer edge points outside of the polyp contours and also a smaller number of points to be transformed based on statistical data from three colonoscopy databases. According to the statistical study we performed, in the colonoscopy images the polyp contours usually belong to gradient domain of neither too large, nor too small gradients, though they can also have stronger or weaker segments. In order to prioritize the gradient domain typical for the polyps, a relative gradient-based thresholding as well as a gradient-weighted voting was introduced in this paper. For evaluating the improvement of the shape deviation tolerance of the classical and fuzzy Hough transforms, the maximum radial displacement and the average radius were used to characterize the roundness of the objects to be detected. The gradient thresholding proved to decrease the calculation time to less than 50% of the full Hough transforms, and the number of the resulting circles outside the polyp’s environment also decreased, especially for low resolution images.

IMPLEMENTASI METODE DETEKSI TEPI CANNY UNTUK MENGHITUNG JUMLAH UANG KOIN DALAM GAMBAR MENGGUNAKAN OPENCV

Edge detection is often used in image processing to find the edge boundaries of image objects and this is important for selecting the edges of image parts. The image edge detection used in this study counts coins in an image, so that it can easily pass through the human eye but not by a computer. In a computer system, it is necessary to provide programs and test data so that the computer can read and count coins like a human. The purpose of this study is to count coins in an image using Canny edge detection and Gaussian filtering methods. The images used in this study are in the form of *jpg and tested using the Visual Studio Code application using OpenCV and Python. The results of this study indicate that the results of the number of coins read from the images inputted to the system can be read properly, with a data accuracy of 90%. Canny's edge detection method can be used to count the number of coins in an image.Keywords: Pengolahan Citra; Deteksi tepi Canny; Gaussian filtering; OpenCV;

The Style Transfer of Photos and Landscape Paintings Based on CycleGAN Combined with Nested Edge Detection Module

Chinese landscape paintings, especially Chinese landscape ink paintings have always been the treasure of the Chinese, or even the world culture. Due to the advancement of the science and knowledge, there are always interests for finding ways to produce Chinese landscape paintings through the way of the technology. In this paper, based on the original CycleGAN model, we are trying to transfer a real-world photograph to a typical Chinese landscape painting. To be specific, the brushwork in Chinese ink paintings contains enormous numbers of distinct and technical brush strokes which makes it extremely hard for CycleGAN to recognize and transfer Chinese ink painting. We improved the brushstroke effect of Chinese ink painting still by incorporating the Holistically Nested Edge Detection (HED) method into the CycleGAN model. The HED module puts the source image and the corresponding generated image into the convolution layer of five stages to generate their respective edge maps. The balanced cross-entropy loss calculated with edge maps is added to the total loss of CycleGAN to train the generator which is confronted with discriminator to improve output results. The addition of HED enables the extraction of edge features from the images, preserving the structural information and enhancing the accuracy of the style transfer, so the detailed of the Chinese ink painting can be transferred better in this sense. Experimental process with model building, training, validating, and predicting concludes that, complementing HED method into the original CycleGAN models well preserved distinct features in the conversion processes from real-world photographs to traditional Chinese landscape paintings.