Title | ||
---|---|---|
Synthetic dataset generation for text recognition with generative adversarial networks |
Abstract | ||
---|---|---|
Automated text recognition is used in autonomous driving systems, search engines, document analysis, and many other applications. There are many techniques to extract text information from scanned documents, but text recognition from arbitrary images is a much harder task. Recently suggested deep learning approaches have demonstrated high-quality results, but they require a huge amount of data to achieve them. The process of collecting and labelling training data to train a deep learning network is costly. In this paper, we suggest an approach for automatic dataset generation for text recognition for arbitrary languages. We use a generative adversarial network structure, which is adapted to generate readable and clear text looking naturally on the image background. We evaluate our approach using SegLink and Textboxes++ text localization models, which were trained on examples generated by SynthText and by variations of our method. The comparison showed the superiority of our method on a subset of the ICDAR 2017 dataset for English and Arabic languages. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1117/12.2558271 | Proceedings of SPIE |
Keywords | DocType | Volume |
dataset synthesis,text recognition,deep learning,generative adversarial network | Conference | 11433 |
ISSN | Citations | PageRank |
0277-786X | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Valeria Efimova | 1 | 0 | 0.34 |
Viacheslav Shalamov | 2 | 0 | 0.34 |
Andrey Filchenkov | 3 | 46 | 15.80 |