Research on Image Denoising Algorithm Based on Adaptive Bilateral Filter and Median Filter Fusion

Abstract

Image denoising remains a fundamental challenge in computer vision applications, where traditional filtering methods often struggle to balance noise reduction effectiveness with edge preservation quality. This research presents an innovative adaptive fusion algorithm that intelligently combines bilateral filtering and median filtering techniques through dynamic weight calculation strategies. The proposed method addresses limitations of existing approaches by implementing noise type detection mechanisms and parameter optimization schemes. Experimental validation on multiple datasets demonstrates superior performance compared to conventional methods, achieving improved Peak Signal-to-Noise Ratio (PSNR) values while maintaining edge sharpness. The adaptive weight calculation strategy enables selective application of filtering techniques based on local image characteristics. Quantitative analysis reveals significant improvements in both noise reduction capabilities and computational efficiency. The proposed fusion framework provides robust performance across different noise conditions, including Gaussian noise and impulse noise scenarios. This research contributes to advancing image enhancement techniques with practical applications in medical imaging, satellite image processing, and multimedia content optimization.