Share Email Print

Proceedings Paper

Image denoising using modified nonlinear diffusion approach
Author(s): Akhilesh R. Upadhyay; Sanjay N. Talbar; Trimbak R. Sontakke
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Partial Differential Equation (PDE) based, non-linear diffusion approaches are an effective way to denoise the images. In this paper, the work is extended to include anisotropic diffusion, where the diffusivity is a tensor valued function, which can be adapted to local edge orientation. This allows smoothing along the edges, but not perpendicular to it. The diffusion tensor is a function of differential structure of the evolving image itself. Such a feedback leads to nonlinear diffusion filters. It shows improved performance in the presence of noise. The original anisotropic diffusion algorithm updates each point based on four nearest-neighbor differences, the progress of diffusion results in improved edges. In the proposed method the edges are better preserved because diffusion is controlled by the gray level differences of diagonal neighbors in addition to 4 nearest neighbors using coupled PDF formulation. The proposed algorithm gives excellent results for MRI images, Biomedical images and Fingerprint images with noise.

Paper Details

Date Published: 17 January 2006
PDF: 8 pages
Proc. SPIE 6059, Image Quality and System Performance III, 60590B (17 January 2006); doi: 10.1117/12.641627
Show Author Affiliations
Akhilesh R. Upadhyay, Institute of Technology and Management (India)
Sanjay N. Talbar, S.G.G.S. Institute of Engineering and Technology (India)
Trimbak R. Sontakke, S.G.G.S. Institute of Engineering and Technology (India)

Published in SPIE Proceedings Vol. 6059:
Image Quality and System Performance III
Luke C. Cui; Yoichi Miyake, Editor(s)

© SPIE. Terms of Use
Back to Top