Subpixel-based image downsampling-some analysis and observation

Often we need to shrink a high resolution image (e.g. 10-mega pixel) in order to display it on a low resolution display (e.g mobile phone). Signal processing theory tells us that optimal decimation requires low-pass filtering with a suitable cutoff frequency followed by downsampling. In doing so, we need to remove lots of details in the original high resolution image. In this paper, we review some little known results on an interesting topic called subpixel rendering, which can provide apparent higher resolution at the expense of color fringing artifacts. We attempt to explain what happens and why this is even possible.