Indonesian Journal of Electrical Engineering and Computer Science
Vol 11, No 7: July 2013

A Gravitational Edge Detection for Multispectral Images

Genyun Sun (China University of Petroleum (East China))
Zhenjie Wang (China University of Petroleum (East China))



Article Info

Publish Date
01 Jul 2013

Abstract

Gravitational edge detection is one of the new edge detection algorithms that is based on the law of gravity. This algorithm assumes that each image pixel is a celestial body with a mass represented by its grayscale intensity and their interactions are based on the Newtonian laws of gravity. In this article, a multispectral version of the algorithm is introduced. The method uses gravitational techniques in combination with metric tensor to detect edges of multispectral images including color images. To evaluate the performances of the proposed algorithm, several experiments are performed. The experimental results confirm the efficiency of the multispectral gravitational edge detection. DOI: http://dx.doi.org/10.11591/telkomnika.v11i7.2808 

Copyrights © 2013