American Journal of Applied Sciences

An Edge Detection Model Based on Virtual Magnetic Field: Application to Digital Color Images

B. Nsiri and B. Bouda

DOI : 10.3844/ajassp.2013.280.293

American Journal of Applied Sciences

Volume 10, Issue 3

Pages 280-293


In computer vision, the edge detection is an essential and difficult problem to study. For this reason, many detectors were developed for gray-level and color images. However, these edge detectors may miss some parts of the edges. In the aim, to deal with this problem, a new approach is proposed. It is based on Virtual Magnetic Field (VMF) in conjunction with Cubical Voxels (CV). The main idea of this approach is to model a color image as a magnetic cube which has the same height and width as the image. The pixels intensities are modeled by the CV model as voxels that are considered by the VMF model as virtual magnetic moments. This technique allows determining easily the most important three operators that are used to provide approximate gradients for each plane color component. The method is tested on synthesized and real images that show promising results.


© 2013 B. Nsiri and B. Bouda. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.