LMMSE frequency merging for demosaicking

For raw images captured by most digital cameras, every pixel has only on color in R, G and B. Kinds demosaicking algorithms are proposed for interpolating the missing two colors. In this article, the relationships inter and intra color channels are analyzed, and basing on the features, we propose a method to divide raw images into sub images and merge them in frequency domain with linear combination. Optimal weights are calculated with estimation values and raw values based on minimum mean square error criteria. Experiments results with different estimations are presented and discussed.