Adaptive image denoising in scale-space using the wavelet transform

C. R. JungJ. Scharcanski

This paper proposes a new method for image denoising with edge preservation using the wavelet transform. At each resolution of the wavelet transform, the coefficients associated do noise and coefficients associated to edges are modeled by Gaussians, and a shrinkage function is assembled. These shrinkage functions are combined in consecutive resolutions, and geometric constraints are applied to preserve edges that are not isolated. The proposed method is adaptive, and performs well for images contaminated by natural and artificial noise.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: