HENet: Forcing a Network to Think More for Font Recognition

  title={HENet: Forcing a Network to Think More for Font Recognition},
  author={Jingchao Chen and Shiyi Mu and Shugong Xu and Youdong Ding},
  journal={2021 3rd International Conference on Advanced Information Science and System (AISS 2021)},
  • Jingchao Chen, Shiyi Mu, +1 author Youdong Ding
  • Published 21 October 2021
  • Computer Science
  • 2021 3rd International Conference on Advanced Information Science and System (AISS 2021)
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… 

Figures and Tables from this paper


DeepFont: Identify Your Font from An Image
This work builds up the first available large-scale VFR dataset, named AdobeVFR, consisting of both labeled synthetic data and partially labeled real-world data, and introduces a Convolutional Neural Network decomposition approach and a novel learning-based model compression approach in order to reduce the DeepFont model size without sacrificing its performance.
Font-ProtoNet: Prototypical Network based Font Identification of Document Images in Low Data Regime
  • N. Goel, Monika Sharma, L. Vig
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
The proposed Font-ProtoNet uses an initial set of classes to learn an embedding and centroid representations that are used to classify novel samples based on euclidean distance, and gives encouraging results by training prototypical networks in few-shot learning settings on a synthetic dataset of 200 font classes.
DropRegion training of inception font network for high-performance Chinese font recognition
A DropRegion method is proposed to generate a large number of stochastic variant font samples whose local regions are selectively disrupted and an inception font network (IFN) with two additional convolutional neural network (CNN) structure elements, which enables end-to-end training.
HanFont: large-scale adaptive Hangul font recognizer using CNN and font clustering
The proposed recognizer, HanFont, is composed of a convolutional neural network model designed to effectively distinguish the detailed shapes and contains a font clustering algorithm to address the issues caused by indistinguishable fonts and untrained new fonts.
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition
Sparse Discriminative Information Preservation for Chinese character font categorization
A new scheme for Chinese character font categorization (CCFC), which applies LBP descriptor based Chinese character interesting points for representing font information through the cooperation between a new Sparse Discriminative Information Preservation (SDIP) for feature selection and NN classifier is proposed.
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
A novel CNN structure for fine-grained classification of Chinese calligraphy styles
Four kinds of styles belonging to standard font are classified with a novel CNN structure where two squeeze-and-excitation modules that emphasize informative feature maps and suppress useless features are embedded after convolution layers, and a Haar transform layer that fuses the features is imposed before softmax layer.
Automatic differentiation in PyTorch
An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.