Research on Image Denoising Algorithm Based on Gaussian Sampling and NLM

This paper presents a mixed noise model that jointly characterizes prevalent noise types in digital image transmission systems. Meanwhile, an LP_NLM denoising algorithm model is proposed. The algorithm is initially optimized on the basis of Non-Local Means (NLM),then progressively refines the denoising process through a multistage asymptotic approach that hierarchically suppresses noise while preserving image textures. In order to systematically evaluate the noise removal ability of LP_NLM algorithm, this study employs multiple denoising algorithms to process images corrupted by complex noise patterns. The evaluation framework incorporates both subjective visual assessment and objective quality metrics. Visual quality assessment serves as the subjective evaluation metric, while structural similarity (SSIM) and peak signal-to-noise ratio (PSNR) are employed as objective quantitative measures.