A Robust Methodology for Reducing Noise and Artifacts in Digital Images using Image Denoising with Filtering Strategy

Image denoising is a critical task in various fields, including medical imaging, remote sensing, and photography, where noise and artifacts can significantly degrade image quality. This study proposes a robust methodology for reducing noise and artifacts in digital images using a hybrid image denoising strategy that integrates Median, Gaussian, and Bilateral filtering techniques. The proposed model was evaluated using the Berkeley Segmentation Dataset and Benchmark (BSDS500) and compared against nine existing models. The results demonstrate that the proposed methodology outperforms existing models across multiple metrics, achieving a Peak Signal-to-Noise Ratio (PSNR) of 32.10 dB, a Structural Similarity Index (SSIM) of 0.890, a Feature Similarity Index (FSIM) of 0.948, and an Edge Preservation Index (EPI) of 0.889. The model also achieved the lowest Mean Squared Error (MSE) of 24.90 and the fastest processing time of 1.20 seconds, highlighting its effectiveness in reducing noise while preserving image details. These findings suggest that the proposed methodology is highly suitable for applications requiring precise and efficient image denoising. The study’s approach offers a comprehensive solution that balances noise reduction with the preservation of critical image features, making it a valuable contribution to the field of image processing.