Grey Relevancy Degree and Improved Eight-Direction Sobel Operator Edge Detection  

作　　者：Yang Yang Lianxin Wei Yang Yang;Lianxin Wei(College of Science, University of Shanghai for Science and Technology, Shanghai, China)

机构地区：[1]College of Science, University of Shanghai for Science and Technology, Shanghai, China

出　　处：《Journal of Signal and Information Processing》2021年第2期43-55,共13页信号与信息处理（英文）

摘　　要：Edge detection is an important aspect to improve image edge quality in image processing. The purpose of edge detection is to identify the points in digital images with great brightness variation. However, the accuracy of traditional edge detection methods in edge extraction is low. For the actual image, the grey edge is sometimes not very clear, the image also contains noise. The detection result of </span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">traditional Sobel operator is relatively accurate, but the detection result is rough and sensitive to noise. To solve the above problems, this paper proposes an improved eight-direction Sobel operator based on grey relevancy degree, which combines 5</span><span style="font-family:""> </span><span style="font-family:Verdana;">×</span><span style="font-family:""> </span><span style="font-family:Verdana;">5 Sobel operator with </span><span style="font-family:Verdana;">a </span><span style="font-family:Verdana;">grey relational degree and a new eight-direction grey relevancy method. The results show that this method can detect the useful information of edge more accurately and improve the anti-noise performance. However, the drawback is that the algorithm is not automatic.Edge detection is an important aspect to improve image edge quality in image processing. The purpose of edge detection is to identify the points in digital images with great brightness variation. However, the accuracy of traditional edge detection methods in edge extraction is low. For the actual image, the grey edge is sometimes not very clear, the image also contains noise. The detection result of </span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">traditional Sobel operator is relatively accurate, but the detection result is rough and sensitive to noise. To solve the above problems, this paper proposes an improved eight-direction Sobel operator based on grey relevancy degree, which combines 5</span><span style="font-family:""> </span><span style="font-family:Verdana;">×</span><span style="font-family:""> </span><span style="font-family:Verdana;">5 Sobel operator with </span><span style="font-family:Verdana;">a </span><span style="font-family:Verdana;">grey relational degree and a new eight-direction grey relevancy method. The results show that this method can detect the useful information of edge more accurately and improve the anti-noise performance. However, the drawback is that the algorithm is not automatic.

关 键 词：Edge Detection Grey Relevancy Eight Directions Sobel Operator 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]