Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders

TL;DR

This paper introduces a cross-modal variational autoencoder that enables conversion between online and offline handwritten characters by sharing a latent space, demonstrating effective mutual modality translation.

Contribution

It proposes a novel Cross-VAE with a space sharing loss to unify online and offline handwriting representations in a shared latent space.

Findings

Successful mutual conversion of online and offline handwritten characters

Effective shared latent space achieved through the proposed loss functions

Qualitative and quantitative analysis confirms the model's performance

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.