DOI: 10.5593/sgem2017/21/S07.004


T. Barbu
Wednesday 13 September 2017 by Libadmin2017

References: 17th International Multidisciplinary Scientific GeoConference SGEM 2017, www.sgem.org, SGEM2017 Conference Proceedings, ISBN 978-619-7408-01-0 / ISSN 1314-2704, 29 June - 5 July, 2017, Vol. 17, Issue 21, 21-28 pp, DOI: 10.5593/sgem2017/21/S07.004


A novel image edge detection technique is proposed in this paper. The considered boundary detection approach uses a nonlinear parabolic partial differential equation (PDE) - based model. We develop a nonlinear anisotropic diffusion scheme consisting in a second-order parabolic equation and some boundary conditions. An effective edge-stopping function is constructed for this PDE model. Then, we construct an explicit iterative numerical approximation scheme for this model, by using the finite-difference method. This numerical discretization scheme is applied on the analyzed image and two results, achieved after different iterations, are considered. The image representing the absolute difference between those two states is then determined and a thresholding procedure is then applied to it. Some morphology-based operations are applied on that image, its edges being determined from these morphologically processes. Numerous experiments and method comparison are performed using the proposed PDE-based edge detection framework.

Keywords: edge detection, PDE model, anisotropic diffusion, numerical approximation scheme, morphology-based operation

Home | Contact | Site Map | Site statistics | Visitors : 0 / 353063

Follow site activity en  Follow site activity INFORMATICS  Follow site activity Papers SGEM2017   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License