Order reprints

Image edge detection based on singular value feature vector and gradient operator

Jiali Tang Yan Wang Chenrong Huang Huangxiaolie Liu Najla Al-Nabhan

*Corresponding author: Chenrong Huang huangcr@njit.edu.cn


This paper presents an edge detection algorithm based on singular value eigenvector and gradient operator. In the proposed algorithm, the singular values of image blocks are first calculated, and the Sobel gradient template is extended to eight other directions. Then the gradient values of image pixels are determined according to the stability of the singular values of image blocks. The determination of gradient threshold is considered from both global and local aspects. After calculating the global and local gradient thresholds of the original image, the gradient threshold of the whole image is determined by weighting function. Then the edge pixels of the image are filtered according to the gradient threshold, and the edge information image of the original image is obtained. The experimental data show that the proposed algorithm can resist a certain degree of noise interference, and the accuracy and efficiency of edge extraction are better than other similar algorithms.

Please supply your name and a valid email address you yourself

Fields marked*are required

Article URL   http://www.aimspress.com/MBE/article/5139.html
Article ID   mbe-17-04-209
Editorial Email  
Your Name *
Your Email *
Quantity *

Copyright © AIMS Press All Rights Reserved