Blind image deblurring using Nash game and the fractional order derivative
F. Z. Semmane, N. Moussaid, Mohammed Ziani · Mathematical Modeling and Computing · 2024
This paper presents an innovative approach to blind image deblurring based on fractional order derivatives and Nash game theory. The integration of fractional order derivatives enhances the deblurring process, capturing intricate image details beyond the capabilities of traditional integer-order derivatives. The Nash game framework is employed to model the strategic interaction between the image and the unknown blur kernel, fostering a cooperative optimization process. Experimental results showcase the proposed method's superiority in terms of both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) when compared to existing methods. The fractional order derivative enhances image structure preservation, while the Nash game facilitates joint optimization of image restoration and blur kernel estimation.