Version: 0.1.4
For a collection of related resources in Hand written OCR research click here
LOCAL ENVIRONMENT
OS : Ubuntu 18.04.3 LTS (64-bit) Bionic Beaver
Memory : 7.7 GiB
Processor : Intel® Core™ i5-8250U CPU @ 1.60GHz × 8
Graphics : Intel® UHD Graphics 620 (Kabylake GT2)
Gnome : 3.28.2
Assuming the libraqm complex layout is working properly, you can skip to python requirements.
sudo apt-get install libfreetype6-dev libharfbuzz-dev libfribidi-dev gtk-doc-tools
- Install libraqm as described here
sudo ldconfig
(librarqm local repo)
python requirements
- pip requirements:
pip install -r requirements.txt
Its better to use a virtual environment OR use conda-
- conda: use environment.yml:
conda env create -f environment.yml
- update datasets.md
- update scripts.md
- synthetic words: printed and handwritten
- indic-iit dataset
- recheck-previous 3 datasets