I have been trying to train Tesseract 4.0 to recognise "customized" font from an engineering blueprint. I've followed the necessary steps using Training Tesseract from here - https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00
I've created a single tiff image from the blueprint page . I am able to create a box file and edit that box file using tesseract4java. The problem is after training all I get is a blank output.
Is it possible to train Tesseract directly from image file without giving initial Text file having the exact font?
