# HENet: Forcing a Network to Think More for Font Recognition

arXiv: https://arxiv.org/abs/2110.10872 · HTML: https://mlsanity.com/paper/2110.10872/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 21 Oct 2021.

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DeepFont: Identify Your Font from An Image](https://mlsanity.com/paper/1507.03196/) (2015)
- [DropRegion Training of Inception Font Network for High-Performance Chinese Font Recognition](https://mlsanity.com/paper/1703.05870/) (2017)

## Built on by (most cited first, 2 of 2)

- [TaCo: Textual Attribute Recognition via Contrastive Learning](https://mlsanity.com/paper/2208.10180/) (2022)
- [Combining OCR Models for Reading Early Modern Printed Books](https://mlsanity.com/paper/2305.07131/) (2023)

## Abstract (arXiv)

Although lots of progress were made in Text Recognition/OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, our proposed method does not require any interactions at the inference stage. Extensive experiments demonstrate that HENet achieves encouraging performance, including on character-level dataset Explor_all and word-level dataset AdobeVFR