Blend text and background images.
Reference:
Jaderberg, Max, et al. “Synthetic data and artificial neural networks for natural scene text recognition.” arXiv preprint arXiv:1406.2227 (2014).
Gupta, Ankush, Andrea Vedaldi, and Andrew Zisserman. “Synthetic data for text localisation in natural images.” CVPR, 2016.
Zhan, Fangneng, Shijian Lu, and Chuhui Xue. “Verisimilar image synthesis for accurate detection and recognition of texts in scenes.” ECCV, 2018.