tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
626 stars 180 forks source link

Create tesseract WordStr box files for given (line) image text pairs #99

Closed Shreeshrii closed 5 years ago

Shreeshrii commented 5 years ago

The line images are cropped and then padded with 10 pixel white border and the new bounding box is used for box file. The cropped images work better for training, leading to faster convergence.

zdenop commented 5 years ago

thanks.