# Selective Style Transfer for Text

## TL;DR

This paper introduces methods for applying style transfer to text images, enabling selective style transfer to specific pixels, and demonstrates its effectiveness in data augmentation for scene text detection.

## Contribution

It proposes two architectures for selective style transfer in text images and evaluates their use as a data augmentation technique for improving scene text detection.

## Key findings

- Selective style transfer is feasible across various text domains.
- Proposed architectures enable transfer to desired image pixels.
- Data augmentation with style transfer boosts text detector performance.

## Abstract

This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.