Existing edge detection algorithms suffer from inefficient edge localization, noise sensitivity, and/or relatively poor automatic detection capability. Contemporary edge detection algorithms can be improved by targeting these problems to help bolster their performance. Grey system theory can be used to resolve the small data and poor information issues in the local information of uncertain systems. An automatic edge detection algorithm was developed in this study based on a grey prediction model to remedy these problems. Noise characteristics in grey images are used to deploy a noise-filtering algorithm based on local features. A mask with twenty-four edge direction information points (345°) was established based on edge line texture features. By compressing the amplitude of the sequence, the randomly oscillated grey prediction sequence can be converted into a smooth, new sequence. The discrete grey model (1,1) (DGM(1,1)) was established based on this new grey prediction sequence to obtain the grey prediction maximum value. A grey prediction image with enhanced edges was obtained by replacing the pixel value in the original image with the maximum grey prediction value. A grey prediction subtraction image with edges separated from non-edge points was also obtained by subtracting the original image from the grey prediction image. The optimal separation threshold in the grey prediction subtraction image can be determined via the global adaptive threshold selection method. The neighborhood search method was then deployed to remove stray points and burrs from the image after the target was separated from the background, creating the final edge image. Experiments were performed on a computer-simulated phantom to find that both the subjective visual effects and objective evaluation criteria are better under the proposed method than several other competitive methods. The proposed edge detection algorithm shows excellent edge detection ability and is highly robust to noise, though the grey prediction model needs further improvement to optimize the run time.

/pdf/adaptive-edge-detection-algorithm-based-on-improved-grey-311avgb8dk.pdf

Adaptive Edge Detection Algorithm Based on Improved Grey Prediction Model

A segmentation process is usually required in order to analyze an image. One of the available segmentation approaches is by detecting the edges on the image. Up to now, there are many edge detection algorithms that researchers have proposed. Thus, the purpose of this systematic literature review is to investigate the available quality assessment methods that researchers have utilized to evaluate the performance of the edge detection algorithms. Due to the vast number of available literature in this area, we limit our search to only open-access publications. A systematic search in five publisher websites (i.e., IEEExplore, IET digital library, Wiley, MDPI, and Hindawi) and Scopus database was carried out to gather resources that are related to the edge detection algorithms. Seventy-three publications that are about developing or comparing edge detection algorithms have been chosen. From these publication samples, we have identified 17 quality assessment methods used by researchers. Among the popular quality assessment methods are visual inspection, processing time, confusion-matrix based measures, mean square error (MSE)-based measures, and figure of merit (FOM). This survey also indicates that although most of the researchers only use a small number of test images (i.e., less than 10 test images), there are available datasets with a larger number of images for digital image segmentation that researchers can utilize.

/pdf/quality-assessment-methods-to-evaluate-the-performance-of-3s53h52132.pdf

Quality Assessment Methods to Evaluate the Performance of Edge Detection Algorithms for Digital Image: A Systematic Literature Review

Overhead power line icing disaster is one of the most noteworthy problem which highly damage the safety of power grid, so it is needed for monitoring in the area. Recently, computer vision and Unmanned Aerial Vehicle (UAV) is developing rapidly, which is suitable for the monitoring of transmission lines icing. Edge detection method is the main priority for automatically measurement of monitoring system based on UAV. There are numerous edge detection methods, but Canny edge detector is considered to be more reliable than some traditional methods. In this paper, a method of improvement Canny using hybrid technique is proposed for more accurate measurements. Traditional Canny operator and improvement Canny operator are compared and analyzed in the simulation. For the comparison the result used are mean square error (MSE), root mean square error (RMSE) and peak signal to noise ratio (PSNR). The simulation results show that the improvement Canny operator using the hybrid technique better than traditional Canny.

Improvement Canny Edge Detection for the UAV Icing Monitoring of Transmission Line Icing

Asbestosis diagnosis algorithm combining the lung segmentation method and deep learning model in computed tomography image

Infrared image segmentation of the wind turbine blade is an important link of wind turbine condition monitoring. Nevertheless, there remain plenty of challenges when the traditional semantic segmentation networks are applied directly to the infrared image segmentation of wind turbine blade, including the blurred boundaries caused by similar thermal radiation of background and blade, the irregularity of edge identification caused by uneven heating, and the hub misidentified as blade. To address these issues, a semantic segmentation neural network based on the basic U-Net is improved for infrared image segmentation of the wind turbine blade. The hierarchical-split depthwise separable convolution block is integrated into the constructed network to have a higher segmentation accuracy. Also, the fusion of convolution layer and batch normalization layer is performed in inference to get a better speed–accuracy tradeoff. The experimental results show that the proposed approach outperforms all the comparing methods, which further demonstrates that the trained network can achieve superior runtime performance and accurate segmentation with excellent anti-interference performance. 

An Improved U-Net Model for Infrared Image Segmentation of Wind Turbine Blade

When a single image segmentation method is used for image segmentation of wind turbine blade images under a complex background, the results obtained are not accurate and complete. This article proposes an image segmentation algorithm that applies morphology to Canny edge detection. It uses morphological opening to erode and dilate the binary image after Canny algorithm processing, and removes redundant edge information to obtain a complete fan blade image. Experimental results show that the results obtained by the image segmentation method proposed here have good integrity and accuracy, and can improve the segmentation effect of the image.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/joe.2018.9113

Yunbo Zuo

Papers

Applying morphology to improve Canny operator's image segmentation method