Image Denoising with Nonlinear Hybrid Diffusion-Modified Perona-Malik Model (NHD-MPM) and Parameter Optimization by Artificial Bee Colony (ABC) Algorithm

Abstract

Image denoising aims to faithfully reconstruct an image from its noise corrupted observation. It tends to improve the degraded image quality for better interpretation and data extraction. Anisotropic diffusion models have reached a good balance between noise removal and edge preserving. But the optimization of the parameters for these models becomes difficult because of the different images and their quality. In this paper, a proposed a hybrid image denoising algorithm based on Nonlinear Hybrid Diffusion -Modified Perona-Malik (NHD-MPM) model. It is performed based on the mean curvature smoothing and Gaussian heat diffusion. The results of this denoising algorithm are combined to diffusion model and the Modified Perona- Malik (MPM) model. In addition the proposed work parameters of the Nonlinear Hybrid Diffusion are optimized via the use of the Artificial Bee Colony (ABC) optimization. In addition, the patch similarity modulus is used as the new structure indicator for the MPM model. The proposed method is thus able to efficiently preserve the edges, textures, thin lines, weak edges, and fine details, meanwhile preventing the staircase effects. Also compared NHD-MPM model with some recently advanced models, the experimental results demonstrated NHD-MPM model has a better detail and texture preservation capability.