Data Augmentation for Historical Documents via Cascade Variational Auto-Encoder

Guanyu Cao, Sei Ichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we introduce a novel model based on Variational Auto-Encoder (VAE) that is able to find subclasses of categories and generate new samples with fidelity to the subclass in an unsupervised way. In generating characters from historical documents, this model helps generated characters to avoid ambiguity in the case where there are multiple writing styles of one character without being labeled. With this model we augment historical Japanese document dataset to make it more balanced. The model is trained in two steps. In the first step, the model learns the data distribution and learns to map character images into basic shape vectors. In the second step, the model learns to generate new samples conditioned on the basic shape vectors. The generated samples are more robust against intra-class multi-modality. With the usage of augmented dataset, the recognition rate is improved. Ablation study is performed to evaluate the effectiveness of data augmentation.

Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages340-345
Number of pages6
ISBN (Electronic)9781728133775
DOIs
Publication statusPublished - 2019 Sep
Event2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019 - Kuala Lumpur, Malaysia
Duration: 2019 Sep 172019 Sep 19

Publication series

NameProceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019

Conference

Conference2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
CountryMalaysia
CityKuala Lumpur
Period19/9/1719/9/19

Keywords

  • Conditional Generation
  • Dataset Augmentation
  • Unsupervised Learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Data Augmentation for Historical Documents via Cascade Variational Auto-Encoder'. Together they form a unique fingerprint.

Cite this