Text and Style Conditioned GAN for Generation of Offline Handwriting Lines

2020/09/01 by Brian Davis, Davis, Brian, Chris Tensmeyer +9 · 8 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction

paper · pdf · doi:10.48550/arxiv.2009.00678

openalex publication_date 2020/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or single-word images, this model generates entire lines of offline handwriting. The model produces variable-sized images by using style vectors to determine character widths. A generator network is trained with GAN and autoencoder techniques to learn style, and uses a pre-trained handwriting recognition network to induce legibility. A study using human evaluators demonstrates that the model produces images that appear to be written by a human. After training, the encoder network can extract a style vector from an image, allowing images in a similar style to be generated, but with arbitrary text.

Citations

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Neural Painters: A learned differentiable constraint for generating brushstroke paintings

Cited by

• ScriptViT: Vision Transformer-Based Personalized Handwriting Generation
• SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design
• Autoregressive Styled Text Image Generation, but Make it Reliable
• Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Model
• Dual Orthogonal Guidance for Robust Diffusion-based Handwritten Text Generation
• FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
• Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation
• Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques

Related

• SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text
• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
• Adversarial Generation of Handwritten Text Images Conditioned on\n Sequences
• SE-GAN: Skeleton Enhanced GAN-based Model for Brush Handwriting Font Generation
• Arbitrary Handwriting Image Style Transfer