tesseractgt: Generate Ground Truth Data for Tesseract

In an early stage (v0.0.4). Check out the guide with a fully developed example and the package documentation.

GIF showing how the tesseractgt GUI works
GIF showing how the tesseractgt GUI works

Step-by-step summary

(Go to the guide for more detailed explanations of each step.)

  1. Install the Tesseract engine, tesseract, and tesseractgt.

  2. Take screenshots to serve as fine-tuning images, and save them in a folder.

  3. Use tesseractgt::create_gt_txt() to create and pre-fill files with the text in the images.

  4. Call the GUI from “Addins > Correct ground truth files” in RStudio or tesseractgt::correct_gt_txt(). Use it to correct the text files created in step 2.

  5. Fine-tune using tesstrain.

Installation 

install.packages("remotes") # if `remotes` is not installed
remotes::install_github("arcruz0/tesseractgt")