Documentation.md

Technical Documentation

Technical Papers and Presentations

Tesseract 4.0 with LSTM

For information about the new LSTM based tesseract engine, please see the documentation.

Manual Pages (3.0x)

The manual pages for tesseract and related training tools (mainly for 3.0x version) are available at following links:

• tesseract
• ambiguous_words
• cntraining
• combine_tessdata
• dawg2wordlist
• mftraining
• shapeclustering
• unicharset_extractor
• wordlist2dawg

plus description of unicharambigs files

Changes to Tesseract

• Release Notes
• Change Log

API/ABI Changes Review

The review of API/ABI changes for Tesseract since 3.00 version has been created with the help of open-source abi-tracker tool. The tool checks all API symbols declared in header files (doesn't take docs into account), so there may be some false positives.

Browse code via Insight.io (master branch)

Documentation of tesseract generated from source code by insight.io can be found at https://www.insight.io/github.com/tesseract-ocr/tesseract

Doxygen (4.00.00dev)

Documentation of tesseract generated on Sat May 20, 2017 from master branch (4.0) by doxygen can be found at https://ub-mannheim.github.io/tesseract/

Doxygen (3.04 from July 2015)

Documentation of tesseract generated from source code as of July 2015 by doxygen can be found on tesseract-ocr.github.io

FAQ

Frequently Asked Questions