[tesseract-ocr] Difficulty in training of the ocr model

2024-01-09 Thread Madhava Raj
Hello group, We are developing a ocr model which extracts the answer from the answer sheet for government school students . I am stuck with the training process itself we had more than 5000 student answer sheets as data but i don't know how to create dataset and train my own ocr model . C

[tesseract-ocr] Train Just a Few Layers

2024-01-09 Thread Simon
Hello everybody, currently I am trying to train just a few layern of the eng_best.traineddata file. I already created 30,000 box gt.txt and .tif files for training specifically for my problem. As I tried to follow the instructions for training tesseract 4 (https://tesseract-ocr.github.io/tes