Showing papers on "Image gradient published in 2022"

The Algorithm of Watershed Color Image Segmentation Based on Morphological Gradient

Abstract: The traditional watershed algorithm has the disadvantage of over-segmentation and interference with an image by reflected light. We propose an improved watershed color image segmentation algorithm. It is based on a morphological gradient. This method obtains the component gradient of a color image in a new color space is not disturbed by the reflected light. The gradient image is reconstructed by opening and closing. Therefore, the final gradient image is obtained. The maximum inter-class variance algorithm is used to obtain the threshold automatically for the final gradient image. The original gradient image is forcibly calibrated with the obtained binary labeled image, and the modified gradient image is segmented by watershed. Experimental results show that the proposed method can obtain an accurate and continuous target contour. It will achieve the minimum number of segmentation regions following human vision. Compared with similar algorithms, this way can suppress the meaningless area generated by the reflected light. It will maintain the edge information of the object well. It will improve the robustness and applicability. From the experimental results, it can be seen that compared with the region-growing method and the automatic threshold method; the proposed algorithm has a great improvement in operation efficiency, which increased by 10%. The accuracy and recall rate of the proposed algorithm is more than 0.98. Through the experimental comparison, the advantages of the proposed algorithm in object segmentation can be more intuitively illustrated.

Comparative analysis between different edge detection techniques on mammogram images using PSNR and MSE

Abstract: Abstract Edge detection is an important technique of image processing and computer vision detecting points where the image properties change at a steady rate. Being operated by detection of brightness discontinuities, it further detects object boundaries within images also. It is used for image segmentation and data extraction in fields like image processing, computer vision, and machine vision. This paper is aimed at description and evaluation of comparative observation of different operators of edge detection in image processing. Pertinently, MATLAB is a development tool being used to find performance of various operators. Besides, the efficiency of the Canny edge detection operator has also been proved to be outperforming as compared to Sobel, Roberts, Prewitt, Zero crossing, and LoG (Laplacian of Gaussian) in the current analysis.

New Aggregation Approaches with HSV to Color Edge Detection

Abstract: Abstract The majority of edge detection algorithms only deal with grayscale images, while their use with color images remains an open problem. This paper explores different approaches to aggregate color information of RGB and HSV images for edge extraction purposes through the usage of the Sobel operator and Canny algorithm. This paper makes use of Berkeley’s image data set, and to evaluate the performance of the different aggregations, the F -measure is computed. Higher potential of aggregations with HSV channels than with RGB channels is found. This article also shows that depending on the type of image used, RGB or HSV, some methods are more appropriate than others.

Fuzzy Logic Approaches in the Task of Object Edge Detection

Abstract: The task of reducing the computational complexity of contour detection in images is considered in the article. The solution to the task is achieved by modifying the Canny detector and reducing the number of passes through the original image. In the first case, two passes are excluded when determining the adjacency of the central pixel with eight adjacent ones in a frame of size 3х3. In the second case, three passes are excluded, two as in the first case and the third one necessary to determine the angle of gradient direction. This passage is provided by a combination of fuzzy rules. The goal of the work is to increase the performance of computational operations in the process of detecting the edges of objects by reducing the number of passes through the original image. The process of edge detection is carried out by some computational operations of the Canny detector with the replacement of the most complex procedures. In the proposed methods, fuzzification of eight input variables is carried out after determining the gradient and the angle of its direction. The input variables are the gradient difference between the central and adjacent cells in a frame of size 3х3. Then a base of fuzzy rules is built. In the first method, four fuzzy rules and one pass are excluded depending on the angle of gradient direction. In the second method, sixteen fuzzy rules themselves set the angle of the gradient direction, while eliminating two passes along the image. The gradient difference between the central cell and adjacent cells makes it possible to take into account the shape of the gradient distribution. Then, based on the center of gravity method, the resulting variable is defuzzified. Further use of fuzzy a-cut makes it possible to binarize the resulting image with the selection of object edges on it. The presented experimental results showed that the noise level depends on the value of the a-cut and the parameters of the labels of the trapezoidal membership functions. The software was developed to evaluate fuzzy edge detection methods. The limitation of the two methods is the use of piecewise-linear membership functions. Experimental studies of the performance of the proposed edge detection approaches have shown that the time of the first fuzzy method is 18% faster compared to the Canny detector and 2% faster than the second fuzzy method. However, during the visual assessment, it was found that the second fuzzy method better determines the edges of objects.

Canny Edge Detection Analysis Based on Parallel Algorithm, Constructed Complexity Scale and CUDA

Abstract: Edge detection is especially important for computer vision and generally for image processing and visual recognition. On the other hand, digital image processing is widely used in multiple science fields such as medicine, X-ray analysis, magnetic resonance tomography, computed tomography, and cosmology, i.e. information collection from satellites, its transferring, and analysis. Any step of image processing, from obtaining the image to its segmentation and object recognition is followed by image noise. The processing speed is vital in popular fields that demand image analysis in real time. In this work, we have proposed an approach of parallel computing of the Canny algorithm using CUDA technology, the complexity of object recognition is analyzed according to the type of the image noise and the level of its density. The sequenced implementation on GPU and the parallel implementation on GPU was considered. The results were analyzed for efficiency and reliability. Also, parallel acceleration is calculated according to the size of the incoming image. The manipulations with the image showed the growth of processing speed of 68 times, whereas the manipulations with the size of the kernel showed the growth of processing speed of 26 times. Another contribution of this work is the analysis of the complexity of object recognition depending on the type of image noise and the level of its density. Furthermore, the increase of Gaussian noise density linearly increases the complexity of object recognition.

Initial Results on the Effectiveness of Distributed Edge Detection for Large Image Data Sets

Abstract: Image data is expanding rapidly, along with technology development, so efficient solutions must be considered to achieve high, real-time performance in the case of processing large image datasets. Parallel processing is increasingly used as an attractive alternative to improve the performance, when using existing distributed architectures but also for sequential commodity computers. It can provide speedup, efficiency, reliability, incremental growth, and flexibility. We present such an alternative and stress the effectiveness of the methods to accelerate computations on a small cluster of PCs compared to a single CPU. Our paper is focused on applying edge detection on large image data sets, as a fundamental and challenging task in image processing and computer vision. Five different techniques, mainly Sobel, Prewitt, LoG, Canny, and Roberts, are compared in a simple experimental setup that includes the OpenCV library functions for image pixels manipulation. Gaussian blur is used to reduce high-frequency components to manage the noise that edge detection is impacted by. Overall, this work is part of a more extensive investigation of image segmentation methods on large image datasets, but the results presented are relevant and show the effectiveness of our approach.

Medical Image Enhancement Based on Laplace Transform, Sobel Operator and Histogram Equalization

Abstract: : Medical image enhancement is one of the most widely used medical image processing techniques in medical domain. Its purpose is to improve the visual effect of the image and facilitate the analysis and understanding of the image by human or machine. The Laplace transform and the Sobel gradient operator are two common ways of performing edge detection, image sharpening and enabling the image to be enhanced. However, each has limitations when used in isolation. The Laplace operator has a good edge detection effect, but it will make the image noise expand; the Sobel operator has a certain ability to smooth the noise, but the edges of the image obtained after processing are rougher. This paper therefore proposes a method based on both Laplace transform and Sobel operator, and histogram equalization of the transformed image is processed to enhance the image. Using a combination of both filtering methods avoids the disadvantage. This method was found to be effective in improving the quality of lung images and skeletal images through several experiments.

Research on edge detection algorithm of work piece defect in machine vision detection system

Abstract: Surface defect detection based on machine vision is widely used in product quality detection in manufacturing industry. To improve the accuracy and efficiency of surface defect detection, an improved defect edge detection algorithm is proposed based on the study of Sobel operator. Firstly, the defect image is collected by the detection platform. Then, the defect image is processed by the median filter to eliminate some small noise and interference. Finally, the improved Sobel operator is used to calculate the gradients in eight directions, then the gradients of each pixel are calculated to obtain the gradient image, and the iterative threshold method is used to segment the gradient image, to extract the defect edge. Experimental results show that the improved Sobel algorithm can improve the shortcomings of easy edge loss, poor noise suppression ability, and insensitivity to edges in other directions, and has good edge continuity, good edge positioning ability, and unilateral performance, which improves the effectiveness of the algorithm.

Camera Calibration and Video Stabilization Framework for Robot Localization

Abstract: Two major issues in robot localization are Camera Calibration (CC) and Video Stabilization (VS). The effectiveness of CC is highly provisional based on adjusting settings, image quality, and image gradient. Recent breakthrough methods employ fixed threshold to calculate pixel difference between frames and preset variables, and neglect slope information causing blurring effect for image frame selected in CC phase. Additionally, contemporary optical flow requires expert manual setting of Gaussian pyramid parameters such as sigma, down scale factor, and number of levels, which consume a lot of time and efforts to train and measure. Apart from that, the localization key challenges of humanoid stereo vision are large motion, motion blur, and defocus blurs of image. Though state-of-the-art approaches used landmark recognition and probabilistic models to overcome those issues, yet localization accuracy is still poor due to image distortion. This work proposed a framework for robot localization via CC and VS methods and triangulation concept. The framework with Fuzzy Camera Calibration (FCC) achieved better results in re-projection error compared to s about 0.85 and 2.62 in pairs based on self-collected dataset, whereas FCC versus Ferstl scored approximately 0.21 and 0.24 in pairs using Time-of-flight camera dataset. For VS, this framework with Fuzzy Optical Flow (FOF) method achieved second rank compared to the state-of-the-art methods such as Farneback, Brox (GPU), LK (GPU), Farneback (GPU), Dual_TVL1, and Simple Flow tested on SINTEL benchmark datasets. Finally, our proposed stereo vision, localization framework also outperformed Mono Vision method vision about 4.07 cm and 61.07 cm subsequently of distance errors.

Comparison of edge discrimination of microbubbles between Sobel and improved mathematics of Canny edge detection

Abstract: Bubble sizes are generated by micro-bubble generators (MBGs) in the water for their effect on the percentage of dissolved oxygen in the water and we find this in aquaculture where oxygen is important to marine life and in many applications. And since these bubbles range in size from 20 to 50, we need to highlight the shape of the bubble and distinguish it, so two Sobel algorithms were used and the Canny method was improved and compared between them, where the edge detection algorithm is sensitive to noise, and therefore, it is easy to lose weak edge information when filtering noise, and it appears ts fixed parameters are weak adaptability. In response to these problems, this paper proposed an improved algorithm based on the Canny algorithm. This algorithm introduced the concept of gravitational field strength to replace the image gradient and obtained the gravitational field strength factor. Two methods for choosing the adaptive threshold based on the average image gradation The size and standard deviation of two types of model images (one containing less edge information, the other containing rich edge information) were subtracted, respectively. The improved Canny algorithm is simple and easy to achieve. Experimental results show that the algorithm can retain more useful information and is more robust in the face of noise.

Memristive Fast-Canny Operation for Edge Detection

Abstract: Memristor-based in- memory computing paradigm is a promising path for edge detection in image preprocessing on end devices that reduces the computational pressure on data centers. However, the implementation of the well-performing Canny operator for edge detection faces challenges in terms of computational time and area overhead when mapped to memristor arrays. In this work, we proposed an efficient memristive one-step implementation of a fast-Canny operator. Exploiting the associative property of multiplication, the conventional Canny operator consisting of Gaussian and Sobel operators is converted into a fast-Canny operator and mapped to an array of nine parallel memristors. Then, the output currents are the final pixels of the edge image. To verify the feasibility of the method, successful edge detection with high accuracy (OIS = 0.73) is achieved in device-aware simulation under device variation (<50%) and image noise ( $\sigma $ = 6%). Additionally, the implementation of the fast-Canny operator on memristor arrays can reduce the processing time by half and save the area of buffer compared to the prior two-convolution Canny operation. Our work suggests that the memristive fast-Canny operator could be a promising and efficient hardware solution for edge detection at the network edge.

Color Image Enhancement Algorithm on the Basis of Wavelet Transform and Retinex Theory

Abstract: For enhance the contrast of low-illuminance images, reduce image noise, and maintain image edge detail information, a color image enhancement algorithm on the basis wavelet transform and Retinex theory is proposed in this paper. First, convert the low-illuminance color image to be enhanced from RGB space to HSV color space, perform wavelet transformation on the brightness component V, and separate several high-frequency and low-frequency children; then use improved single-scale Retinex algorithm to enhance the low-frequency offspring, reduce the influence of external light factors on the image and retain the edge texture of the image; the high-frequency children are subjected to blur enhancement processing to achieve image denoising and enhancement. The saturation component S is enhanced by segmented exponential transformation to make the image color more suitable for human visual habits; finally, the processed image is changed back to a color RGB image. The experimental results show that the edge texture of the image processed by the algorithm are maintained well, the contrast has been significantly improved, color distortion is avoided, and it has a good visual effect.

Improved edge detection algorithm for canny operator

Abstract: Canny edge detection algorithm is widely used in many fields.but the problem of noise pollution in the actual working environment, the effect of image edge detection is susceptible to the pepper salt noise, and the results of Canny algorithm detect fault and lost edge details. In order to remove pepper salt noise from the image and extract edge information of the area of interest from the image, an image edge detection algorithm based on improving Canny operator is proposed. The proposed algorithm designs a novel filter to replace the Gaussian filter in the traditional algorithm to filter the pepper and salt noise in the picture. The original algorithm uses only a gradient template in both horizontal and vertical directions in calculating the image gradient, while the improved algorithm adds the gradient templates in both 45°and 135°. Finally, the maximum inter-class variance method is adopted to determine the optimal threshold when making the high and low threshold connection. It can be seen that in edge detecting the image with pepper salt noise, the proposed algorithm can effectively filter the pepper salt noise in the picture, and the edge detection results are more accurate without losing detail.

Alignment and fusion of visible and infrared images based on gradient-domain processing

Abstract: An image fusion of different modal images, such as visible and far-infrared images, is an important image processing technique because different modal images can compensate for each other. Many existing image fusion algorithms assume that different modal images are perfectly aligned. However, that assumption is not satisfied in many practical situations. In this paper, we propose an image alignment and fusion algorithm with gradient-domain processing. First, we extract the gradient maps from both modality images. Then, assuming disparities between the two gradient maps, candidate gradient maps for the target fused image are generated by selecting the gradient having larger power from different modality images pixel-by-pixel. A key observation is as follows. If the assumed disparity is wrong, the fused image includes ghost edges. If the assumed disparity is correct, the single edge is preserved without the ghost edge in the fused image. Therefore, we evaluate the gradient power in the region-of-interest of the fused image with different diparities. Then, we can align images based on the disparity associated with the minimum gradient power. Finally, we apply gradient-based image fusion with the aligned image pairs. We experimentally validate that the proposed approach can effectively align and fuse the visible and far-infrared images.

Subpixel edge detection algorithm based on improved Gaussian fitting and Canny operator

Abstract: : In image processing, image edge is often used as a basic feature in higher-level image processing. Edge detection technology is the basis of image processing technologies such as image measurement, image segmentation, image compression and pattern recognition. It is one of the important research topics in digital image processing. In this paper, we explore the image edge and pixel data, and propose an optimization model for sub-pixel edge extraction, image distortion correction and image edge segmentation. We preprocess the image with Gaussian filter, median filter and morphological close operation to reduce the impact of lighting environment and noise on the image. After edge detection with Canny operator, we use two-dimensional interpolation to Gaussian fit the edge points in the gradient direction to obtain the sub-pixel edge, and then search the pixel points to obtain the pixel order of the graphic outline and display it with different colors. Finally, we summarize the model, adjust the search range and extend it to the case of low definition of the original image. We can obtain high-precision contour edges of low pixels through technical means.

Performance analysis of gradient based image edge detection

Abstract: Edge detection is a dynamic area of research and it gives support to higher level image analysis. Edge detection is a method of image processing used to make points in a digital image with discontinuities, sharp modifiers in the image brightness. Edge detection methods used in this work are Sobel, Prewitt, Roberts, Laplacian of Gaussian and Canny. The performance evaluation measures such as accuracy and specificity calculated from the Berkeley Segmentation dataset. Edge detection is used for object detection which offers various applications like medical field, industrial field, biometrics etc.

Research on Image Edge Detection Based on Improved Canny Operator

Abstract: Sorting the workpiece is one of the key steps in the production practice of workpieces, and machine vision is often used in the sorting process to detect workpiece edge information and screen out other information such as noise. Aiming at the problems of gaussian filtering denoising and artificial threshold setting in traditional Canny edge detection algorithm, an improved Canny algorithm is proposed for edge detection of workpiece. The algorithm uses the MeanShift algorithm instead of Gaussian filtering, which preserves the edge information while denoising. This new algorithm uses the maximum inter-class variance (OSTU) algorithm to obtain the adaptive optimal threshold and improve the adaptability of the algorithm. Experimental results show that under the subjective visual and objective evaluation, the algorithm has significantly improved the edge detection effect of the traditional Canny algorithm.

Canny Sub-pixel Edge Detection Method Based on Threshold Segmentation and Markov Field Correction

Abstract: Markov field correction based on threshold segmentation Canny sub-pixel edge detection algorithm is of great significance for image position correction, accurate target segmentation and contour fitting. First, we adjust the brightness and contrast of the image to highlight the target area. Secondly, classical edge detection algorithms such as Sobel and Canny algorithms are used to extract the contour of the target image. However, we find that the performance of these algorithms will decline when there is noise interference. Therefore, in order to eliminate the side effects of noise, Perona-Malik (PM) model and Markov field correction method based on threshold segmentation are used to denoise the image. Then the above two algorithms are combined to extract the image contour. The experimental results show that the image contour extracted by Canny algorithm has high accuracy.