HENet: Forcing a Network to Think More for Font Recognition

Jingchao Chen, Shiyi Mu, Shugong Xu, Youdong Ding

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2021 3rd International Conference on Advanced Information Science and System, AISS 2021 - Conference Proceedings
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450385862
DOIs
Publication statusPublished - 26 Nov 2021
Externally publishedYes
Event3rd International Conference on Advanced Information Science and System, AISS 2021 - Sanya, China
Duration: 26 Nov 202128 Nov 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Advanced Information Science and System, AISS 2021
Country/TerritoryChina
CitySanya
Period26/11/2128/11/21

Keywords

  • font recognition
  • neural networks
  • pluggable

Fingerprint

Dive into the research topics of 'HENet: Forcing a Network to Think More for Font Recognition'. Together they form a unique fingerprint.

Cite this