I have lot of pages written in particular font but unfortunately original soft copy of those pages is not available. I need to OCR those pages to make them editable again.
By default tesseract doesn't read that font and need training to OCR that font. I want someone with good experience with Tesseract, train tessarect for that font.
1. After training tessarect should be able to OCR pages with minimum 99% accuracy.
2. I also want to learn entire process so in future I can train tessarect myself for other fonts, so coder will also help me train tessarect at my end using the training tiff and box files he/she create.
A sample tiff file attached.
I will provide more tiff files for testing and also tell exact font name used in files to winning coder.