Comparative Analysis of Denoising Performance of Image Filters

Images are frequently impacted by noise due to various factors that cause distortion and a loss of critical information. This noise can interfere with important tasks like video processing, image analysis and object tracking, making denoising a vital aspect of modern image processing systems. Image denoising aims to suppress noise while preserving important image features, particularly edges and textures. Although many filters exist, their effectiveness varies depending on the noise type and application constraints. This paper systematically benchmarks four classic denoising techniques: Median, Non-Local Means, Wiener, and Lee filters across synthetic and real-world noise scenarios. Using metrics such as Peak Signal-to-Noise Ratio (PSNR), Mean Signal-to-Noise Ratio (MSNR), and Mean Absolute Error (MAE), filter strengths have been assessed. The results provide insight into the relative performance of each method, supporting informed filter selection for real-time and resource-constrained applications such as mobile imaging, surveillance, and medical diagnostics.