Implementation of a FPGA-ARM-based Canny Edge Detection System

In this paper ,a new method for edge detection in multispectral imags is presented. It is based on the use of the Self-Organizing Map (SOM), Peano scan and a conventional edge detector. The method presented in this paper order the vectors of the original image in such a way that vectors that are near each other according to some similarity criterium have scalar ordering values near each other. This is achieved using a 2D self-organizing map and the Peano scan. After ordering, the original vector image reduces to a gray-value image, and a conventional edge detector can be applied. In this paper, the Laplace and the Canny edge detectors are used. It is shown, that using the proposed method sit is possible to find the same relevant edges that R-ordering based methods find. Furthermore, it is also possible to find edges in images which consist of metameric colors, i.e. images in which every pixel vector maps into the same location in RGB space. This is not possible using conventional edge detectors which use an RGB image as input. Finally, the new method is tested with a real-world airplane image, giving results comparable with R-ordering based methods.© (1999) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Ultrasound (US) breast cancer images is one of the most complicated medical images to extract the desired area of interest. It is often difficult to separate the tumor region from the background tissues. Therefore, tumor segmentation is the challenging problems in the computed aided diagnosis. Among many image segmentation techniques, a generalized gradient vector flow (GGVF) method is one of the popular techniques. It is based on vector transformation of the edge map of the gray scale image. GGVF introduces a non-uniform diffusion to preserve the large gradient of the boundary area and smooth the gradients caused by noise and speckles. However, the improper numerical iteration of GGVF may lead the false contours or the existing noise and finally the snake could not reach the true boundary. In this paper, the new vector field analysis for breast tumor US image segmentation is proposed. The GGVF vector field will be derived from the edge map of the original image. The algorithm analyzes the GGVF vectors in terms of the entropy of the angle of vectors in the corresponding window. The windows will be vertically and horizontally flipped, then the entropy will be evaluated again. Next, the ratio of the entropy before and after flip will be determined to be the classifier of the boundary and non-boundary. The algorithm has been tested on the real US breast tumor images with a set of ground truth images hand-drawn by radiologists. The proposed algorithm is compared with conventional edge detectors such as Sobel and Canny operator. The numerical experiments show that the proposed techniques lead to a better segmentation accuracy with the reference to the conventional edge detection.

In this paper, a novel edge detection method that computes image gradient using the concept of Center of Mass (COM) is presented. The algorithm runs with a constant number of operations per pixel independently from its scale by using integral image. Compared with the conventional convolutional edge detector such as Sobel edge detector, the proposed method performs faster when region size is larger than 9×9. The proposed method can be used as framework for multi-scale edge detectors when the goal is to achieve fast performance. Experimental results show that edge detection by COM is competent with Canny edge detection.

Image edge detection significantly preserves the important structural properties in an image, while reducing the amount of data and filters out useless information. Since edge detection is in the forefront of image processing for object detection, it is crucial to have a good understanding of edge detection algorithms. This paper introduces the Canny edge detection algorithm and the implementation of the Canny edge-detection algorithm on an FPGA. Custom implementation in FPGAs, using a combination of hardware and software co-design, allows real-time processing, providing a good trade-off between performance and flexibility. The results show that FPGAs are good alternatives, which can be used to off-load these computationally-intensive and repetitive functions as co-processors and the capability of supporting canny edge detection for real-time image processing.

As an indispensable measuring instrument, the pointer instrument has been widely used in the fields of industrial production. While the manual instrument identification has problems of higher labor intensity, higher rate of misjudgment and lower production, we take advantage of computer vision to deal with the images of pointer instrument dials. Two algorithms are proposed for image edge detection: structured random forests edge detection and canny edge detection, Hough transform is used to recognize the straight lines of the pointer, then the automation of instrument identification can be realized. Our results show that the accuracy of the dials printed by the two methods can meet the production requirements.

Accurate segmentation of COVID‐19 CT images is crucial for reducing the severity and mortality rates associated with COVID‐19 infections. In response to blurred boundaries and high variability characteristic of lesion areas in COVID‐19 CT images, we introduce CDSE‐UNet: a novel UNet‐based segmentation model that integrates Canny operator edge detection and a Dual‐Path SENet Feature Fusion Block (DSBlock). This model enhances the standard UNet architecture by employing the Canny operator for edge detection in sample images, paralleling this with a similar network structure for semantic feature extraction. A key innovation is the DSBlock, applied across corresponding network layers to effectively combine features from both image paths. Moreover, we have developed a Multiscale Convolution Block (MSCovBlock), replacing the standard convolution in UNet, to adapt to the varied lesion sizes and shapes. This addition not only aids in accurately classifying lesion edge pixels but also significantly improves channel differentiation and expands the capacity of the model. Our evaluations on public datasets demonstrate CDSE‐UNet’s superior performance over other leading models. Specifically, CDSE‐UNet achieved an accuracy of 0.9929, a recall of 0.9604, a DSC of 0.9063, and an IoU of 0.8286, outperforming UNet, Attention‐UNet, Trans‐Unet, Swin‐Unet, and Dense‐UNet in these metrics.

Edge detection is a fundamental process in image processing with significant implications across multiple domains. Within the realm of object detection, the accurate delineation of image perimeters forms the bedrock for subsequent analysis. In this study, we present an optimized Laplacian Edge Detection algorithm tailored for efficient implementation in hardware.Leveraging approximation methodologies and strategic pipelining, we streamline complex operations, thereby reducing latency and resource consumption. Our implementation, realized through the Verilog Hardware Description Language (VHDL), stands as a testament to the efficacy of our approach. Through rigorous optimization and meticulous comparison with conventional Sobel edge detection, we demonstrate superior performance metrics, including enhanced Area utilization, reduced Time Delay, and improved Power Efficiency. This work underscores the importance of methodological refinement and technological innovation in advancing edge detection techniques for practical applications. Keywords: Laplacian, Sobel, Kernel, Pixel range, Area, Power

Machine vision is very important for ensuring the success of intelligent transportation systems, particularly in the area of road maintenance. For this reason, many studies had been focusing on automatic image-based crack detection as a replacement for manual inspection that had depended on the specialist’s knowledge and expertise. In the image processing technique, the pre-processing and edge detection stages are important for filtering out noises and in enhancing the quality of the edges in the image. Since threshold is one of the powerful methods used in the edge detection of an image, we have therefore proposed a modified Otsu-Canny Edge Detection Algorithm in the selection of the two threshold values as well as implemented a multi-resolution level fixed partitioning method in the analysis of the global and local threshold values of the image. This is then followed by a statistical measure in selecting the edge image with the best global threshold. This study had utilized the road crack image dataset that were obtained from Crackforest. The results had revealed the proposed method to not only perform better than the conventional Canny edge detection method but had also shown the maximum value derived from the local threshold of 5x5 partitioned image outperforming the other partitioned scales.

In this paper we compare different edge detectors based on peak signal to noise ratio on Echocardiographic images. Edge detection is a critical element in image processing, since edges contain a major function of image information. The function of edge detection is to identify the boundaries of homogeneous regions in an image based on properties such as intensity and texture.We have taken Perwitt edge detector, Robarts edge detector, LoG edge detector, Canny edge detector, and Sobel edge detector for this comparison and study.

Additive manufacturing (AM), or 3D printing, has revolutionized the fabrication of complex parts, but assessing their quality remains a challenge. Quality assessment, especially for the interior part geometry, relies on post-print inspection techniques unsuitable for real-time in situ analysis. Vision-based approaches could be employed to capture images of any layer during fabrication, and then segmentation methods could be used to identify in-layer features in order to establish dimensional conformity and detect defects for in situ evaluation of the overall part quality. This research evaluated five image segmentation methods (simple thresholding, adaptive thresholding, Sobel edge detector, Canny edge detector, and watershed transform) on the same platform for their effectiveness in isolating and identifying features in 3D-printed layers under different contrast conditions for in situ quality assessment. The performance metrics used are accuracy, precision, recall, and the Jaccard index. The experimental set-up is based on an open-frame fused filament fabrication printer augmented with a vision system. The control system software for printing and imaging (acquisition and processing) was custom developed in Python running on a Raspberry Pi. Most of the segmentation methods reliably segmented the external geometry and high-contrast internal features. The simple thresholding, Canny edge detector, and watershed transform methods did not perform well with low-contrast parts and could not reliably segment internal features when the previous layer was visible. The adaptive thresholding and Sobel edge detector methods segmented high- and low-contrast features. However, the segmentation outputs were heavily affected by textural and image noise. The research identified factors affecting the performance and limitations of these segmentation methods and contributing to the broader effort of improving in situ quality assessment in AM, such as automatic dimensional analysis of internal and external features and the overall geometry.

Abstract: Object detection is one step in object recognition in the field of computer vision. The edges of the image characterize the boundaries that distinguish it from other objects and are therefore a very important problem in image processing. Accurate Image Edge Detection can significantly reduce the amount of data and filter out useless information while retaining important structural properties in the image. Since edge detection is at the forefront of image processing for object detection, it is very important to have a good understanding of edge detection algorithms. In this study, applying canny edge detection using python and OpenCV and also compared with other image processing methods. The result is that Canny edge detection has a better performance compared to other algorithms such as LoG (Laplacian of Gaussian), Robert, Prewitt and Sobel.

Integration of image processing in order to detect red blood cells (RBCs) in human urine enables technology to reduce medical technician’s manual counting time and error factor. The general objective of this study was to detect and count the red blood cells in human urine using Canny Edge Detection (CED) and Circle Hough Transform (CHT) algorithms. CED is an edge detection algorithm used in order to identify a great variety of edges in an image. CHT is one of the features of the Hough Transform. Specifically, CHT is used in order to detect circular objects. The basis of the CHT operation will be dependent on the circular edges detected by the CED. In order to identify a specific circle size, the minimum and maximum radius must be set. Particularly, to differentiate the RBCs from other cells such as white blood cells. For this study, the minimum radius was 4 pixels while the maximum was 6. Compared to the manual counting of a medical technician, the automated counting of the device produced a percent error of 9.561% and an average counting time of 0.4561 seconds per sample.

Object contour detection plays an important role in image processing. Many edge and object contour detectors have been proposed, such as, Canny edge detector, ACM, and level set methods. However, those detection methods often cannot provide the fully edge and object contour perfectly. In the ACM and level set methods, the initial contour of object has to be specified by a user in advance, and the successful segmentation results highly depend on the given initial object contour. In addition, the ACM and level set methods are significantly sensitive to noise. Giving an initial contour of object is not required for Canny edge detector, but it may bring about "broken edge problem." To solve the broken edge problem, a feature-based disconnected edge segments (FBDES) linker is provided in this paper. For extracting objects from an image, in this paper Canny edge detector is first used to detect the object contour, and then the FBDES linker is employed to link the disconnected edge segments based on the features of the gray-level difference at vicinity of, the gradient and gradient direction on, and the length of the line segment connecting two disconnected edge segments. The experimental results show that the FBDES linker can give more impressive object segmentation results than the level set method.

As autonomous driving technology becomes more and more popular, its safety is also attracting attention. Regarding the automatic driving of vehicles, the detection of road markings is particularly important. This paper improves the lane edge detection part of the Hough transform lane line detection method. Because the traditional Canny operator edge detection method is good for image processing, but the detection time is long, this paper replaces the Canny algorithm with the Robert operator edge detection method. The sub-edge detection method can improve the detection speed of lane line extraction. In MATLAB, by using multiple edge detection operators to perform edge detection on the same image 100 times, and taking the average of the detection time, it is found that the Robert operator takes a shorter time in the detection process than the Canny operator; Then the Robert operator and Canny operator are respectively fused into the Hough transform lane line detection. After 100 times, the same image is detected, and the running time is statistically averaged for comparison and analysis. The Robert operator is better than the Canny operator. The time taken is reduced by 0.15191 s. The simulation results show that the integration of Robert operator in Hough transform lane line detection improves the real-time performance of lane detection.

Feature detection is a fundamental technique in broad fields of image processing, pattern recognition and computer vision. A digital image in general contains objects, edges, noises and background. Critical changes in properties of objects can be captured via detecting sharp variations in image brightness. The edges can be detected via numerous approaches on a basis of image intensity changes. Edge broken and false detection are typical problems using classical methods, which will result in information loss and feature deformity. The notion of optimization is thus introduced into edge detection. The Canny edge detector and Ant Colony Optimization (ACO) detector are among the most successful and effective approaches for edge detection. The Canny edge detector is designed to capture edges by searching local optima of the gradient of the intensity. It is susceptible to noises presenting on the raw images, so details of images could be slightly changed when Gaussian smoothing is applied. To improve accuracy, the adaptive edge tracing scheme is proposed. On the other hand, artificial intelligence has also been introduced. Being one of metaheuristic optimization approaches, the evolutionary computing oriented ACO becomes a promising approach for feature capturing without necessity of smoothing filters. Selection of maximum intensity difference as the path visibility function for ACO will contribute better to generate true edges and avoid false edges. Both the adaptive Canny edge detection and enhanced ACO are proposed in this article. Comparative studies are also conducted to evaluate the edge detection qualities. The outcomes are analyzed and evaluated from both qualitative and quantitative points of view, where merits and drawbacks of the two schemes have been indicated.