Hyperspectral images (HSIs) are often corrupted by noise during an acquisition process, e.g., Gaussian noise, salt and pepper noise, deadlines, strip, and many others. This project proposes an image restoration algorithm based on Higher Order Singular Value Decomposition algorithm (HOSVD). The HOSVD acts as fast preconditioner. Instead of dealing as pixels the image is processed as tensor. This project reduces the noises that occur in remote sensing satellite images. The satellite images are degraded by the noise such as Gaussian noise, Impulse noise, Strip noise etc. The tensor of the degraded image is added with tensor of Gaussian, Impulse, Strip noise. The Singular values are extracted from the degraded image which controls intensity of Gaussian, Impulse and Strip noise tensor. This process gets repeated iteratively to get the restored image. The higher order singular value decomposition (HOSVD) of the degraded tensor is obtained very fast and so could be used as a preconditioner. Iterative median filtering for restoration of images corrupted by mixed noise is proposed. The boundary condition for the iteration is based on minimum distance between any two successive iterations is less than a threshold value. Experimental results show that proposed system has higher convergence speed. The complexity of an image restoration process reduces highly further we measures Peak Signal Noise Ratio (PSNR) and Mean Square Error (MSE). The PSNR values appear to be high while the MSE values appear to be low.

Keywords : Image Restoration, Hyperspectral Image (HSI), Mixed Noise, HOSVD, Iterative Median Filter.