Essentially it is looking at the large letters (or pieces of them) to guess how the small letters should look.
And as JTxt notes above, sometimes it chooses the wrong large letter. Even on the third-to-last line it couldn't get one of the letters correct. The output looks like "HKO" while the actual chart has "HKG" -- but since there is no larger "G" for the algorithm to use as an example, it ended up with a different but similar shape. This could probably be improved by the other SR techniques they mention that use libraries of sample images.
[...] there is plenty of patch redundancy within a single image L. Let p be a pixel in L, and P be its surrounding patch (e.g., 5 × 5), then there exist multiple similar patches P1,...Pk in L (inevitably, at sub-pixel shifts). These patches can be treated as if taken from k different low-resolution images of the same high resolution “scene”, thus inducing k times more linear constraints (Eq. (1)) on the high-resolution intensities of pixels within the neighborhood of q ∈ H (see Fig. 3b). For increased numerical stability, each equation induced by a patch Pi is globally scaled by the degree of similarity of Pi to its source patch P. [...]
[...] Assuming sufficient neighbors are found, this process results in a determined set of linear equations on the unknown pixel values in H. Globally scale each equation by its reliability (determined by its patch similarity score), and solve the linear set of equations to obtain H.
Then they also add patches at different scale by making a few more versions of the image which have been scaled down by various amounts, and doing comparisons between the target patch and patches in those images too. If good matches are found, they can then use the original higher-resolution original patch that yielded the match when it was shrunk.
The M first shows on the third from the bottom, but not very clear, but tries to reconstruct it; then it uses that M to replace the M the second from the bottom, finally it guesses that W (only known as a 4x3 pixel blur on the bottom line)is a M.
It's also interesting that the bottom M is skewed out a little on it's top right corner to match the fuzzy W shape.
>Fig. 6 [the eye chart] compares our unified SR result against ground truth. In Fig. 7 [baby with hat] we compare our method to results from [11,13] and [9]. Note that our results are comparable, even though we do not use any external database of low-res/highres pairs of patches [11, 13], nor a parametric learned edge model [9]. Other examples with more comparisons to other methods can be found in the paper’s website.
But their bottom line is mostly correct because their process also uses larger versions of the same pattern to replace the smaller ones.
So, there was not a much larger T, so it made a little fuzzball instead. So I wrote "?".
How about it's what they output when they are not sure?
Most real-world OCR, though, deals with single-scale fonts, and this reconstruction technique may have limited applicability.
Their explanation for it:
"The lines of letters have been recovered quite well due to the existence of cross-scale patch recurrence in those image areas. However, the small digits on the left margin of the image could not be recovered, since their patches recurrence occurs only within the same (input) scale. Thus their resulting unified SR constraints reduce to the “classical” SR constraints (imposed on multiple patches within the input image). The resulting resolution of the digits is better than the bicubic interpolation, but suffers from the inherent limits of classical SR [3, 14]."
So it's guessing based on the larger characters. Neat.
Here's their last line:
DKN?MULJSPAVMRA?C?OVZO
Here's the actual:
DKNTWULJSPXVMRAHCFOYZG
(from what I can read.)
( http://1.bp.blogspot.com/-VgvutrSWaFk/T4VI-2tDH2I/AAAAAAAAAX... )
This could probably help ocr.
Other than this, I think Genuine Fractals and BenVista PhotoZoom give similar results.