tesseract-ocr/tesseract

Is it possible to convert tesseract traineddata to other format?

Open

#1743 opened on Jul 4, 2018

View on GitHub
 (4 comments) (0 reactions) (0 assignees)C++ (74,090 stars) (10,622 forks)batch import
help wantedtraineddata

Description

I'm wondering if it's possible to convert tesseract traineddata to other format so that it can be used by Core ML?

Contributor guide

Tech stack
cpp
Domain
datamobile
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
Tesseract traineddata formatCore ML model formatC++ programmingOCR internals
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
15
Research direction
Start by studying the Tesseract traineddata file format, particularly in the source files under ccutil/tessdata.*. Examine the LSTM recognition model structure used in Tesseract 4. Research Core ML model conversion tools and determine compatibility. Review any existing community efforts or forks that attempt such conversion. The issue comments may provide additional context.