Salt-and-pepper noise removal by a spectral conjugate gradient method

Denoising is an important problem in signal processing. This paper proposes an efficient two-phase method for salt-and-pepper noise removal. In the first phase, adaptive median filter is used to detect the contaminated pixels. Then in the second phase, the candidate pixels will be restored by minimizing a regularization functional. To end of this, a spectral conjugate gradient method is considered. Its global convergence result can be established under some suitable conditions. Experimental results show that the proposed approach is efficient and practical.