Re: [tesseract-ocr] How to correctly define CMakeLists.txt for Tesseract?

On Monday, February 19, 2024 at 4:49:07 AM UTC-5 raphael.s...@gmail.com wrote: I solved the issue, thanks to the help and suggestions, and explanations, I kindly received in StackOverFlow In case someone has a similar issue in the future, the suggestion on StackOverflow was to use CMake's INT

Re: [tesseract-ocr] How to correctly define CMakeLists.txt for Tesseract?

Any reason why to use an external 3rd party app that is not available on all platforms instead of cmake native function which is available everywhere cmake is? Zdenko ut 20. 2. 2024 o 18:02 Tom Morris napísal(a): > On Monday, February 19, 2024 at 4:49:07 AM UTC-5 raphael.s...@gmail.com > wrote

[tesseract-ocr] Trying to train a new font (LCD screen style), unable to get error rate under 40%

I have been trying to retrain tesseract to read characters on a LCD screen, like 0 with a slash, certain V, M, N, A s. My setup: Using tesseract 5.3.2, on a Debian 12 machine for training. I used the code found here https://github.com/astutejoe/tesseract_tutorial/blob/main/split_training_text.py