A general geometric augmentation tool for text images in the CVPR 2020 paper "Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition". We provide the tool to avoid overfitting and gain robustness of text recognizers.
Note that this is a general toolkit. Please customize for your specific task. If the repo benefits your work, please cite the papers.
- Distortion
- Stretch
- Perspective
To transform an image with size (H:64, W:200), it takes less than 14ms using a 2.5GHz CPU. It is possible to accelerate the process by calling multi-process batch samplers in an on-the-fly manner, such as setting "num_workers" in PyTorch.
Modify from https://github.com/Canjie-Luo/Text-Image-Augmentation.git.