Structural-Tensor-Driven Dynamic Window and Dual Kernel Weighting for a Fast Non-Local Mean Denoising Algorithm
Jing Mao, Lianming Sun, Jie Chen · Modelling—International Open Access Journal of Modelling in Engineering Science · 2025
To address the limitations of traditional non-local mean (NLM) denoising algorithms in terms of neighborhood similarity metrics, weight calculation, and computational efficiency, this paper proposed a structural-tensor-driven and dynamic window-based fast non-local mean denoising algorithm with dual kernel weighting. First, a Gaussian–Tukey dual-kernel weighting function was designed to optimize similarity metrics. Then, spatial neighborhood features were adopted. By measuring both grayscale similarity and spatial correlation, the weight distribution rationality was further enhanced. Second, structural tensor eigenvalues were used to quantify regional structural properties. A dynamic window allocation function was designed to adaptively match search window sizes to different image regions. Finally, an integral image acceleration mechanism was proposed, significantly improving algorithm execution efficiency. Experimental results demonstrated that the proposed algorithm achieved both excellent denoising performance and edge/texture preservation capabilities. In high-noise environments, its Peak Signal-to-Noise Ratio (PSNR) outperformed the Gauss kernel non-local mean algorithm by an average of 1.96 dB, while Structural Similarity (SSIM) improved by an average of 5.7%. Moreover, the algorithm’s execution efficiency increased by approximately 7–11 times, indicating strong potential for real-time application in digital image processing.