Image noise reduction based on applying adaptive thresholding onto PDEs methods

Abstract

In this study the authors present a novel image denoising method based on applying adaptive thresholding on partial differential (PDEs) methods. In the proposed method the authors utilise the adaptive thresholding to blend the total variation filter with anisotropic diffusion filter. The adaptive thresholding has a high capacity to adapt and change according to the amount of noise. More specifically, applying a hard thresholding on the higher noise areas, whereas, applying soft thresholding on the lower noise areas. Therefore, the authors can successfully remove the noise effectively and maintain the edges of the image simultaneously. Based on the adaptation and stability of the adaptive thresholding we can achieve; optimal noise reduction and sharp edges as well. Experimental results demonstrate that the new algorithm consistently outperforms other reference methods in terms of noise removal and edges preservation, in addition to 4.7 dB gain higher than those in the other reference algorithms.

Keywords

• image denoising
• image segmentation
• partial differential equations
• edge detection
• filtering theory
• reference algorithms
• edge preservation
• noise removal
• sharp edges
• optimal noise reduction
• anisotropic diffusion filter
• total variation filter
• PDE method
• partial differential equation
• image denoising method
• adaptive thresholding
• image noise reduction