# STEFANN: Scene Text Editor using Font Adaptive Neural Network

## TL;DR

This paper introduces STEFANN, a neural network-based method for editing text in images at the character level, enabling error correction, text restoration, and reusability by generating and replacing characters while maintaining visual consistency.

## Contribution

The paper presents a novel neural network approach for character-level text editing in images, combining font and color preservation for the first time.

## Key findings

- Effective text modification demonstrated on COCO-Text and ICDAR datasets.
- Achieves structural and visual consistency in edited text.
- Outperforms existing methods in qualitative and quantitative evaluations.

## Abstract

Textual information in a captured scene plays an important role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our knowledge, there is no significant prior work that aims to modify the textual information in an image. The ability to edit text directly on images has several advantages including error correction, text restoration and image reusability. In this paper, we propose a method to modify text in an image at character-level. We approach the problem in two stages. At first, the unobserved character (target) is generated from an observed character (source) being modified. We propose two different neural network architectures - (a) FANnet to achieve structural consistency with source font and (b) Colornet to preserve source color. Next, we replace the source character with the generated character maintaining both geometric and visual consistency with neighboring characters. Our method works as a unified platform for modifying text in images. We present the effectiveness of our method on COCO-Text and ICDAR datasets both qualitatively and quantitatively.