An edge detection refinement algorithm based on improved sobel operator
SHEN De-hai
E Xu
HOU Jian
Abstract：In order to solve the shortcomings of low edge position accuracy and coarser edge of the traditional Sobel Operator, an improved algorithm was proposed , the algorithm increases 135°and 45°directions templates based on the original two directions templates , obtains the gradient image through Non -Minimum Suppression and local standard deviation to improve the edge positioning accuracy and enhance edge strength .Finally com-bines the gradient image in 3 ×3 neighborhood with a gradient threshold combined edge direction .Experiments show that the algorithm not only solves the problem of the Sobel , but also obtains more consistent and crisp ed-ges.
Keywords：edge detectionsobel operatorlocal standard deviationedge refinement
Publication Date：2014-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 256-260 )