Modality conversion of handwritten patterns by cross variational autoencoders

Taichi Sumi, Brian Kenji Iwana, Hideaki Hayashi, Seiichi Uchida

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

9 Citations (Scopus)

Abstract

This research attempts to construct a network that can convert online and offline handwritten characters to each other. The proposed network consists of two Variational Auto-Encoders (VAEs) with a shared latent space. The VAEs are trained to generate online and offline handwritten Latin characters simultaneously. In this way, we create a cross-modal VAE (Cross-VAE). During training, the proposed Cross-VAE is trained to minimize the reconstruction loss of the two modalities, the distribution loss of the two VAEs, and a novel third loss called the space sharing loss. This third, space sharing loss is used to encourage the modalities to share the same latent space by calculating the distance between the latent variables. Through the proposed method mutual conversion of online and offline handwritten characters is possible. In this paper, we demonstrate the performance of the Cross-VAE through qualitative and quantitative analysis.

Original languageEnglish
Title of host publicationProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
PublisherIEEE Computer Society
Pages407-412
Number of pages6
ISBN (Electronic)9781728128610
DOIs
Publication statusPublished - Sept 2019
Event15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australia
Duration: Sept 20 2019Sept 25 2019

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363

Conference

Conference15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Country/TerritoryAustralia
CitySydney
Period9/20/199/25/19

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Modality conversion of handwritten patterns by cross variational autoencoders'. Together they form a unique fingerprint.

Cite this