There are some things that may be useful to keep in mind when Working with OCR images.
The first thing is that you have to do, is to scan the document
After that things could go two ways, the first is that if you're making OCR in a with a digital PDF which the source is a digital document.
In that case, you'll be good with the OCR builtin of Okular.
The second path is when you have a physical document and then you scan it, in that case, you'll have to do a little bit of extra work.
After the Document is scanned you could use GIMP in order to adjust the brightness and contrast. In GIMP you could open a PDF two different ways, the first one is using pages as layers recommended when the output you want is in PDF format as well.
However, since the method we're going to use need each page as individual image in order to be an input for Tesseract OCR, we're going to import each PDF page as an image.
Then for each image go to Colors --- Brightness and Contrast and adjust the settings accordingly as yu see the image looks clearer, I recommend Brightness 20 and Contrast 80 as starting point, but remember to tweak values accordingly.
After that in the terminal type tesseract {gimp_img.png} {output_name.png} in the terminal with the files in the current folder.