I am trying to build and optical character recognition system for recognizing car license plat (Indonesian licence plat), unfortunately there is no training set available but I found the font, I try to generate the training data by convolve  the image of license plat letter with kernels (somethings like gaussian blur,box blur) using python, but it does not resemble real data, here is the font look like:
[![font][1]][1]

and I want to generate individual letter, that look like this:

[![plat kendaraan][2]][2]

Do you have any idea how to generate training data like above picture, ?
thank you

  [1]: https://i.sstatic.net/sSFB6.png
  [2]: https://i.sstatic.net/K8FGu.jpg