Adaptive Hybrid Bilateral Filter for Efficient Image Denoising in Noisy Environments

Image denoising is a critical task in image processing, vital for improving visual quality and enhancing the performance of subsequent computer vision tasks. This paper introduces a new Adaptive Hybrid Bilateral Filter (AHBF), which combines Bilateral Filtering, Wavelet Thresholding, and Adaptive Median Filtering to achieve robust noise reduction while maintaining image details. Unlike conventional bilateral filtering, AHBF dynamically selects the most effective denoising method based on local noise characteristics, ensuring superior noise suppression without excessive smoothing. The performance of AHBF is compared against standard filters, such as the Median Filter, Linear Filter, Adaptive Median Filter (AMF), Weighted Median Filter (WMF), Hybrid Median Filter (HMF), and Bilateral Filter. The results show that AHBF outperforms these existing methods in terms of Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Correlation Coefficient across different noise densities. Moreover, proposed technique performs excellent in terms of different types of parameters and save more accurate information as compared to existing methods.