Title :
A well-balanced flow equation for noise removal and edge detection
Author :
Barcelos, Celia Aparecida Zorzo ; Boaventura, Maurílio ; Silva, Evanivaldo Castro, Jr.
Author_Institution :
Fed. Univ. of Uberlandia, Brazil
fDate :
7/1/2003 12:00:00 AM
Abstract :
An anisotropic nonlinear diffusion equation for image restoration is presented. The model has two terms: the diffusion term and the forcing term. The balance between these terms is made in a selective way, in which boundary points and interior points of the objects that make up the image are treated differently. The optimal smoothing time concept, which allows for finding the ideal stop time for the evolution of the partial differential equation is also proposed. Numerical results show the proposed model´s high performance.
Keywords :
edge detection; image denoising; image restoration; image segmentation; interference suppression; nonlinear equations; partial differential equations; random noise; anisotropic diffusion equation; diffusion term; edge detection; flow equation; forcing term; ideal stop time; image restoration; image segmentation; noise removal; nonlinear equation; object boundary points; object interior points; partial differential equation; Computed tomography; Differential equations; Filters; Image edge detection; Image reconstruction; Magnetic resonance imaging; Nonlinear equations; Optical imaging; Partial differential equations; X-ray imaging;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2003.814242
