Existing Edge Detection Methods Research Articles

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.

EDGE DETECTION TECHNIQUE BASED ON BILATERAL FILTERING AND ITERATIVE THRESHOLD SELECTION ALGORITHM AND TRANSFER LEARNING FOR TRAFFIC SIGN RECOGNITION

The traffic sign identification and recognition system (TSIRS) is an essential component for autonomous vehicles to succeed. The TSIRS helps to collect and provide helpful information for autonomous driving systems. The information may include limits on speed, directions for driving, signs to stop or lower the speed, and many more essential things for safe driving. Recently, incidents have been reported regarding autonomous vehicle crashes due to traffic sign identification and recognition system failures. The TSIRS fails to recognize the traffic signs in challenging conditions such as skewed signboards, scratches on traffic symbols, discontinuous or damaged traffic symbols, etc. These challenging conditions are presented for various reasons, such as accidents, storms, artificial damage, etc. Such traffic signs contain an ample amount of noise, because of which traffic sign identification and recognition become a challenging task for automated TSIRS systems. The proposed method in this paper addresses these challenges. The sign edge is a helpful feature for the recognition of traffic signs. A novel traffic sign edge detection algorithm is introduced based on bilateral filtering with adaptive thresholding and varying aperture size that effectively detects the edges from such noisy images. The proposed edge detection algorithm and transfer learning is used to train the Convolutional Neural Network (CNN) models and recognize the traffic signs. The performance of the proposed method is evaluated and compared with existing edge detection methods. The results show that the proposed algorithm achieves optimal Mean Square Error (MSE) and Root Mean Square Error (RMSE) error rates and has a better Signal to Noise Ratio (SNR) and Peak Signal to Noise Ratio (PSNR) ratio than the traditional edge detection algorithms. Furthermore, the precision rate, recall rate, and F1 scores are evaluated for the CNN models. With the German Traffic Sign Benchmark database (GTSRB), the proposed algorithm and Inception V3 CNN model gives promising results when it receives the edge-detected images for training and testing.

Multiscale hierarchical attention fusion network for edge detection

Edge detection is one of the basic challenges in the field of computer vision. The results of most recent methods produce thick edges and background interference. The images generated by these networks must be postprocessed with non-maximum suppression (NMS). To tackle the problem, we propose a novel edge detection model that allows the network to concentrate on learning the contextual features of an image, thereby obtaining more accurate pixel edges. To obtain abundant multi-granularity features of image high-level features, we introduce multi-scale feature stratification module (MFM). Then, we increase the constraint between pixels through the edge attention module (EAM), so that the model can obtain stronger feature extraction ability. These new approaches can improve the ability of describing edges of models. Evaluating our method on two popular benchmark datasets, the edge image predicted by this method is superior to existing edge detection methods in subjective perception and objective evaluation indexes.

Recent advances on image edge detection: A comprehensive review

Edge detection is one of the most important and fundamental problems in the field of computer vision and image processing. Edge contours extracted from images are widely used as critical cues for various image understanding tasks such as image segmentation, object detection, image retrieval, and corner detection. The purpose of this paper is to review the latest developments on image edge detection. Firstly, the definition and properties of edges are introduced. Secondly, the existing edge detection methods are classified and introduced in detail. Thirdly, the existing widely used datasets and evaluation criteria for edge detection methods are summarized. Finally, future research directions for edge detection are elaborated.

A novel edge detection method based on dynamic threshold neural P systems with orientation

The existing edge detection methods can often encounter several common shortcomings: discontinuous edges, weak edges, easy to be affected by noise, and difficulty in setting gradient thresholds. To address these shortcomings, this paper proposes a neural-like computing model, called dynamic threshold neural P systems with orientation, termed as ODTNP systems. In addition to the spiking and dynamic threshold mechanisms, ODTNP systems also integrate the gradient magnitude and gradient direction information. The combination of these mechanisms is beneficial to ODTNP systems to achieve edge detection. Based on ODTNP systems, a novel edge detector is developed. The proposed ODTNP-based edge detector is evaluated on the benchmark Berkeley segmentation data set (BSDS500) and is compared with five baseline edge detection methods and four state-of-the-art deep-learning-based edge detection methods. Experimental results demonstrate the availability and effectiveness of the proposed edge detector.

Mini Kirsch Edge Detection and Its Sharpening Effect

In computer vision, edge detection is a crucial step in identifying the objects’ boundaries in an image. The existing edge detection methods function in either spatial domain or frequency domain, fail to outline the high continuity boundaries of the objects. In this work, we modified four-directional mini Kirsch edge detection kernels which enable full directional edge detection. We also introduced the novel involvement of the proposed method in image sharpening by adding the resulting edge map onto the original input image to enhance the edge details in the image. From the edge detection performance tests, our proposed method acquired the highest true edge pixels and true non-edge pixels detection, yielding the highest accuracy among all the comparing methods. Moreover, the sharpening effect offered by our proposed framework could achieve a more favorable visual appearance with a competitive score of peak signal-to-noise ratio and structural similarity index value compared to the most widely used unsharp masking and Laplacian of Gaussian sharpening methods. The edges of the sharpened image are further enhanced could potentially contribute to better boundary tracking and higher segmentation accuracy.

Mini Kirsch Edge Detection and Its Sharpening Effect

In computer vision, edge detection is a crucial step in identifying the objects’ boundaries in an image. The existing edge detection methods function in either spatial domain or frequency domain, fail to outline the high continuity boundaries of the objects. In this work, we modified four-directional mini Kirsch edge detection kernels which enable full directional edge detection. We also introduced the novel involvement of the proposed method in image sharpening by adding the resulting edge map onto the original input image to enhance the edge details in the image. From the edge detection performance tests, our proposed method acquired the highest true edge pixels and true non-edge pixels detection, yielding the highest accuracy among all the comparing methods. Moreover, the sharpening effect offered by our proposed framework could achieve a more favorable visual appearance with a competitive score of peak signal-to-noise ratio and structural similarity index value compared to the most widely used unsharp masking and Laplacian of Gaussian sharpening methods. The edges of the sharpened image are further enhanced could potentially contribute to better boundary tracking and higher segmentation accuracy.

Edge Detection Using the Bhattacharyya Distance with Adjustable Block Space

In this paper, we propose a new edge detection method for color images, based on the Bhattacharyya distance with adjustable block space. First, the Wiener filter was used to remove the noise as pre-processing. To calculate the Bhattacharyya distance, a pair of blocks were extracted for each pixel. To detect subtle edges, we adjusted the block space. The mean vector and covariance matrix were computed from each block. Using the mean vectors and covariance matrices, we computed the Bhattacharyya distance, which was used to detect edges. By adjusting the block space, we were able to detect weak edges, which other edge detections failed to detect. Experimental results show promising results compared to some existing edge detection methods.

MSB based Cellular Automata for Edge Detection

A vitalcrucial pre-processing phase in image processing, computer vision and machine learning applications is Edge Detection which detects boundaries of foreground and background objects in an image. Discrimination between significant edges and not so important spurious edges highly affects the accuracy of edge detection process. This paper introduces an approach for extraction of significant edges present in images based on cellular automata. Cellular automata is a finite state machine where every cell has a state. Existing edge detection methods are complex to implement so they have large processing time. These methods tend to produce non-satisfactory results for noisy images which have cluttered background. Some methods are so trivial that they miss part of true edges and some methods are so complex that they tend to give spurious edges which are not required. The advantage of using cellular computing approach is to enhance edge detection process by reducing complexity and processing time. Parallel processing makes this method fast and computationally imple. MATLAB results of proposed method performed on images from Mendeley Dataset are compared with results obtained from existing edge detection techniques by evaluation of MSE and PSNR values Results indicate promising performance of the proposed algorithm. Visually compared, the proposed method produces better results to identify edges more clearly and is intelligent enough to discard spurious edges even for cluttered and complex images.

Edge detection in potential filed using the correlation coefficients between the average and standard deviation of vertical derivatives

Edge detection is an essential task in the interpretation of potential field data. Many existing edge detection methods are the functions composed by the horizontal derivative and vertical derivative of potential field data. The edges recognized by those methods are bigger than the true edges and when the depths of the geological bodies are different, the edges will be detected fuzzy and difficult to identify the edges accurately. In this paper, we present a new method to delineate the edges of the sources, which is based on the correlation coefficients between the average and standard deviation of vertical derivatives in a sliding window. The algorithm of this method is very simple. The zero value of the correlation coefficients is used to delineate the geological edges. It's clear to see the edges with the zero contours which will lead to continuous and clear detected edges and the method shows the edges more precisely. Moreover, the anomalies in different depths can be detected in the same degree and are insensitive to noise. The measure is initially applied on the synthetic gravity and magnetic data. The tests of theoretical models indicate that the new method could detect the edges of models in different depths and the position is in good accordance with the models' edges. Finally, this method is applied to gravity data from a portion of Vientiane Basin, Laos. As a result, the method is helpful in recognizing geologic fractures clearly. Moreover, it shows more geologic details with smaller window size and gives superior results with higher quality data.

모폴로지를 이용한 마스크 기반 에지 검출 알고리즘에 관한 연구

In this digital information era, utilization of images are essential for various media, and the edge is an important characteristical information of an object in images that includes the size, location, direction and etc. Many domestic and international studies are being conducted in order to detect these edge. Existing edge detection methods include Sobel, Prewitt, Roberts, Laplacian, LoG and etc. which apply fixed weight value. As these existing edge detection methods apply fixed weight mask to the image, edge detection characteristic appears slightly insufficient. Accordingly, in order to supplement these problems, this study used bottom-hat transformation from mathematical morphology and opening operation in improving the image and proposed an algorithm that detects for the edge after calculating mask-based gradient. And to evaluate the performance of the proposed algorithm, a comparison was made against the existing Sobel, Roberts, Prewitt, Laplacian, LoG edge detection methods, in illustrating visual images, and similarities were compared by calculating the MSE value based on the standard of each image.

변형된 히스토그램 평활화를 적용한 에지 검출에 관한 연구

Edge detection is one of the important technologies to simplify images in the text, lane and object recognition implementation process, and various studies are actively carried out at home and abroad. Existing edge detection methods include a method to detect edge by applying directional gradient masks in spatial space, and a mathematical morphology-based edge detection method. These existing detection methods show insufficient edge detection results in excessively dark or bright images. In this regard, to complement these drawbacks, we proposed an algorithm using the Sobel and histogram equalization among the existing methods.

Image Edge Detection Based on Complex Ridgelet Transform

For the defects of the existing edge detection methods those can’t well guarantee the robust anti-noise character and the continuity of edges detected simultaneously, a new kind of image edge detection method is proposed which is based on the complex ridgelet transform and Laplace operator. First, the scalar one-dimensional wavelet transform in the traditional ridgelet transform is replaced by dual-tree complex wavelet transform, so that the ridgelet transform has translation invariance, and then the image is denoised by the complex ridgelet transform. Second, the Laplace operator convolutes the coefficients of the complex ridgelet transform so as to tell whether the points are edge points. The experiments show that this method has a better robust anti-noise character, and could reserve edge information in the image better at the same time of image de-noising, which could extract the object profile efficiently.

Improved Edge Detection Method by using Weighted Support Vector Machines

dge detection plays considerable part in recent years to various image processing applications. Detection of edge results for noise free images becomes easy and it is not applicable to practical applications .The quality of images for a practical case is degraded by noise. Detection of edges for noise image becomes more difficult task in several numbers of edge detection methods such as K means clustering, and SVM classification methods. All of these methods produce best edge detection results, but still the detection rate of methods needs to improve. In this paper presented a new weighted support vector machines (WSVM) method for edge detection. It uses different edge detection features as input to WSVM for edge detection process. This method enhances edge detection results by reducing the working out time and improvement the image quality it can be compared to existing edge detection methods. The overall performance of proposed WSVM edge detection results is high than the existing methods. Keywords---Weighted support vector machines, Edge detection, Gradients, Image processing.

RIDED-2D: A RULE-BASED INSTANTANEOUS DENOISING AND EDGE DETECTION METHOD FOR 2D RANGE SCAN LINE

Edge detection is often regarded as a basic step in range image processing by virtue of its crucial effect. The majority of existing edge detection methods cannot satisfy the requirement of efficiency in many industrial applications due to huge computational costs. In this paper, a novel instantaneous method, named RIDED-2D is proposed for denoising and edge detection for 2D scan line in range images. In the method, silhouettes of 2D scan line are classified into eight types by defining a few new coefficients. Several discriminant criteria on large noise filtering and edge detection are stipulated based on qualitative feature analysis on each type. Selecting some feature point candidates, a practical parameter learning method is provided to determine the threshold set, along with the implementation of an integrated algorithm by merging calculation steps. Because all the coefficients are established based on distances among the points or their ratio, RIDED-2D is inherently invariant to translation and rotation transformations. Furthermore, a forbidden region approach is proposed to eliminate interference of the mixed pixels. Key performances of RIDED-2D are evaluated in detail by including computational complexity, time expenditure, accuracy and stability. The results indicate that RIDED-2D can detect edge points accurately from several real range images, in which large noises and systematic noises are involved, and the total processing time is less than 0.1 millisecond on an ordinary PC platform using the integrated algorithm. Comparing with other state-of-the-art edge detection methods qualitatively, RIDED-2D exhibits a prominent advantage on computational efficiency. Thus, the proposed method qualifies for real-time processing in stringent industrial applications. Besides, another contribution of this paper is to introduce CPU clock counting technique to evaluate the performance of the proposed algorithm, and suggest a convenient and objective way to estimate the algorithm's time expenditure in other platforms.