Text Renderer

Generate text images for training deep learning OCR model (e.g. CRNN). Support both latin and non-latin text.


  • Ubuntu 16.04
  • python 3.5+

Install dependencies:

pip3 install -r requirements.txt


By default, simply run python3 main.py will generate 20 text images and a labels.txt file in output/default/.


Use your own data to generate image

  1. Please run python3 main.py --help to see all optional arguments and their meanings. And put your own data in corresponding folder.
  2. Config text effects and fraction in configs/default.yaml file(or create a new config file and use it by --config_file option), here are some examples:
Effect nameImage
Origin(Font size 25)origin
Perspective Transformperspective
Random Croprand_crop
Light borderlight border
Dark borderdark border
Random char space bigrandom char space big
Random char space smallrandom char space small
Middle linemiddle line
Table linetable line
Under lineunder line
Reverse colorreverse color
Text colorfont_color
Line colorline_color
  1. Run main.py file.

Strict mode

For no-latin language(e.g Chinese), it's very common that some fonts only support limited chars. In this case, you will get bad results like these:


Select fonts that support all chars in --chars_file is annoying. Run main.py with --strict option, renderer will retry get text from corpus during generate processing until all chars are supported by a font.


You can use check_font.py script to check how many chars your font not support in --chars_file:

python3 tools/check_font.py checking font ./data/fonts/eng/Hack-Regular.ttf chars not supported(4971): ['第', '朱', '广', '沪', '联', '自', '治', '县', '驼', '身', '进', '行', '纳', '税', '防', '火', '墙', '掏', '心', '内', '容', '万', '警','钟', '上', '了', '解'...] 0 fonts support all chars(5071) in ./data/chars/chn.txt: []

Generate image using GPU

If you want to use GPU to make generate image faster, first compile opencv with CUDA. Compiling OpenCV with CUDA support

Then build Cython part, and add --gpu option when run main.py

cd libs/gpu
python3 setup.py build_ext --inplace

Debug mode

Run python3 main.py --debug will save images with extract information. You can see how perspectiveTransform works and all bounding/rotated boxes.



GitHub - Sanster/text_renderer: Generate text images for training deep learning ocr model
Generate text images for training deep learning ocr model - GitHub - Sanster/text_renderer: Generate text images for training deep learning ocr model