A novel approach for edge detection based on the theory of universal gravity

  • Authors:

  • Genyun Sun;Qinhuo Liu;Qiang Liu;Changyuan Ji;Xiaowen Li

  • Affiliations:

  • State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China;State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China;State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China;College of Engineering, University of Philippines Diliman, Manila, Philippines;State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China

  • Venue:
  • Pattern Recognition
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper presents a new, simple and effective low-level processing edge detection algorithm based on the law of universal gravity. The algorithm assumes that each image pixel is a celestial body with a mass represented by its grayscale intensity. Accordingly, each celestial body exerts forces onto its neighboring pixels and in return receives forces from the neighboring pixels. These forces can be calculated by the law of universal gravity. The vector sums of all gravitational forces along, respectively, the horizontal and the vertical directions are used to compute the magnitude and the direction of signal variations. Edges are characterized by high magnitude of gravitational forces along a particular direction and can therefore be detected. The proposed algorithm was tested and compared with conventional methods such as Sobel, LOG, and Canny using several standard images, with and without the contamination of Gaussian white noise and salt & pepper noise. Results show that the proposed edge detector is more robust under noisy conditions. Furthermore, the edge detector can be tuned to work at any desired scale.