Style Transfer and Extraction for the Handwritten Letters Using Deep Learning

TL;DR

This paper presents a deep learning approach using a conditioned autoencoder to extract and transfer handwriting styles, demonstrating significant improvements over existing methods in style quality and generalization to unseen writers.

Contribution

The study introduces a novel deep autoencoder model that effectively extracts and transfers handwriting styles, outperforming previous benchmarks and analyzing style separation in the latent space.

Findings

Improved performance metrics over state-of-the-art methods

Effective style transfer to unseen writers

Latent space clearly separates different handwriting styles

Abstract

How can we learn, transfer and extract handwriting styles using deep neural networks? This paper explores these questions using a deep conditioned autoencoder on the IRON-OFF handwriting data-set. We perform three experiments that systematically explore the quality of our style extraction procedure. First, We compare our model to handwriting benchmarks using multidimensional performance metrics. Second, we explore the quality of style transfer, i.e. how the model performs on new, unseen writers. In both experiments, we improve the metrics of state of the art methods by a large margin. Lastly, we analyze the latent space of our model, and we see that it separates consistently writing styles.