Title :
Improved De-noising Algorithm on Heat Equation
Author_Institution :
Sch. of Math. & Comput. Sci., Guilin Univ. of Electron. Technol., Guilin, China
Abstract :
The heat equation has equal diffusions both in the gradient and the tangent direction, which can strongly smooth the important character of the image while de-noising. In order to better preserve the characteristic of an image, we must take different diffusions in different regions; therefore a weight function is used to induce diffusion in the gradient direction. The experimental results show improvements of the proposed model.
Keywords :
gradient methods; image denoising; denoising algorithm; gradient direction; heat equation; weight function; Astronomy; Genetics; Image denoising; Image processing; Laplace equations; Mathematics; Noise reduction; Nonlinear equations; Remote sensing; Temperature;
Conference_Titel :
Genetic and Evolutionary Computing, 2009. WGEC '09. 3rd International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-0-7695-3899-0
DOI :
10.1109/WGEC.2009.177