Verisimilar Image Synthesis for Detection and Recognition of Texts

The proposed scene text image synthesis technique starts with two types of inputs including “Background Images” and “Source Texts” as illustrated in column 1 and 2 in Fig. 1.

Data and Resources

Cite this as

Fangneng Zhan, Shijian Lu, Chuhui Xue (2024). Dataset: Verisimilar Image Synthesis for Detection and Recognition of Texts. https://doi.org/10.57702/bprwwjsb

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.1807.03021
Author Fangneng Zhan
More Authors
Shijian Lu
Chuhui Xue
Homepage https://arxiv.org/abs/1704.03155