Reconstructing missing pixel information to provide a full output image

A method of processing a sampled input image having pixels which can have missing information at pixel locations to reconstruct an output image therefrom, comprising the steps of:

• a) providing a mask for the sampled image to identify valid and non-valid pixel locations;
• b) interpolating by convolution with at least one finite impulse response (FIR) filter(s) applied to the information at valid pixel locations to produce reconstructed information for non-valid pixel locations;
• and
• (c) adaptively normalizing the reconstructed information for the non-valid pixel locations produced by applying the FIR filter(s) to the mask so that the valid pixels and the reconstructed information at non-valid pixel locations provide a reconstructed image, wherein the reconstructed image, G(i,j), is defined by:
• G ⁡ ( i , j ) = 1 N ⁡ ( i , j ) ⁢ ∑ b = - n / 2 n / 2 ⁢ ∑ a = - m / 2 m / 2 ⁢ K ⁡ ( a , b ) ⁢ F ⁡ ( i - a , j - b ) ⁢ M ⁡ ( i - a , j - b )
• where
• F(i,j) is the sampled input image;
• M(i,j) is a binary mask indicating the location of the image samples, where M(i,j)=1, Otherwise, M(i,j)=0,
• K(a,b) is an FIR filter;
• N(i,j) is the adaptive normalization which is given by:
• N ⁡ ( i , j ) = ∑ b = - n / 2 n / 2 ⁢ ∑ a = - m / 2 m / 2 ⁢ K ⁡ ( a , b ) ⁢ M ⁡ ( i - a , j - b ) ;
• ⁢ and
• (i,j) labels the sampling positions of the reconstructed image.