# Exploring Font-independent Features for Scene Text Recognition

arXiv: https://arxiv.org/abs/2009.07447 · HTML: https://mlsanity.com/paper/2009.07447/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network](https://mlsanity.com/paper/2108.09661/) (2021)
- [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://mlsanity.com/paper/2208.00438/) (2022)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2108.01343/) (2021)
- [Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition](https://mlsanity.com/paper/2402.13643/) (2024)
- [Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks](https://mlsanity.com/paper/2210.06924/) (2022)
- [IterVM: Iterative Vision Modeling Module for Scene Text Recognition](https://mlsanity.com/paper/2204.02630/) (2022)
- [Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching](https://mlsanity.com/paper/2203.06696/) (2022)

## Abstract (arXiv)

Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or writing) styles also pose severe challenges to STR. These methods, where font features and content features of characters are tangled, perform poorly in text recognition on scene images with texts in novel font styles. To address this problem, we explore font-independent features of scene texts via attentional generation of glyphs in a large number of font styles. Specifically, we introduce trainable font embeddings to shape the font styles of generated glyphs, with the image feature of scene text only representing its essential patterns. The generation process is directed by the spatial attention mechanism, which effectively copes with irregular texts and generates higher-quality glyphs than existing image-to-image translation methods. Experiments conducted on several STR benchmarks demonstrate the superiority of our method compared to the state of the art.