I want to extract text from some images with messy backgrounds.
First step was switching to gray scale, applying an edge detection algorithm, and then cleaning up a little bit.
I want to use the tesseract OCR to extract the text from it, but it's not good enough to find it, as the background is quite messed up still. (I tried with a cleaner version and it's doing ok).
So, could anyone recommend an algorithm, or a type of algo, that would help me clean up this image and just get the text? (it will always have this font).
One idea I had was to try to remove all the clumps that are "larger" than the font, which is pretty thin.
ps: hopefully it's the right stackexchange site.