[tesseract-ocr] Tesseract not making correct predictions even on training data

Hi, I was trying to train a tesseract model. I used my own tif/box pairs. During training tesseract reported high accuracy on training data. However, after completing the training, when I used tesseract to make predictions, it made completely incorrect predictions even on training images. As a

[tesseract-ocr] Re: Dot Matrix Fonts and Tesseract's Connected Component Analysis

Hi, I've a similar requirement to read dot-matrix fonts but I'm not sure where to begin this from since I'm new to Tesseract. Could you please share references/guide. Thanks. On Friday, March 22, 2019 at 12:41:11 PM UTC+5:30, ameera...@gmail.com wrote: > > I am trying to fine-tune Tesseract f

Re: [tesseract-ocr] Trained data for E13B font

Please also search for existing MICR traineddata files. On Thu, Jun 6, 2019 at 1:09 PM ElGato ElMago wrote: > So I did several tests from scratch. In the last attempt, I made a > training text with 4,000 lines in the following format, > > 110004310510< <02 :4002=0181:801= 0008752 <00039 ;