SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation

2026-07-07

AI Summary

Existing handwritten text synthesis methods struggle to model cursive trajectories, preserve structural details, and generate high-resolution, sharp glyphs, often producing blurred or fragmented strokes due to the absence of explicit edge constraints. This work proposes a generative adversarial network–based framework with spiral modulation for handwritten text synthesis. It introduces a Star-Spiral module that integrates star operations with modulated elliptical spiral fully connected layers to accurately trace complex stroke patterns. A spiral-modulated discriminator is employed for multi-domain defect detection, complemented by a Sobel-regularized edge reconstruction loss to enhance boundary sharpness. Evaluated on both English and Vietnamese datasets, the proposed method significantly outperforms state-of-the-art approaches, generating highly realistic glyphs with consistent cross-lingual stylistic fidelity and effectively reducing error rates in downstream handwritten text recognition tasks.

Abstract

Training robust handwriting recognition (HTR) systems requires massive amounts of annotated data, which is often difficult to acquire. While synthetic handwriting generation offers a practical solution to expand training sets, existing models struggle with several core issues. First, previous approaches, even MLP-based models fail to effectively trace cursive handwriting due to fixed-grid spatial receptive field. Second, their CNN-relied discriminators usually lose structural details through aggressive downsampling, making broken connections difficult to detect. Third, existing architectures are either limited to linear feature interactions or too expensive for high-resolution synthesis. Finally, existing approaches lack explicit edge constraints, often resulting in blurred stroke boundaries. To address these challenges, this study proposes a Spiral-Modulated Handwriting Synthesis framework based on Generative Adversarial Networks (SpiS-GAN). Our generator employs Star-Spiral Blocks combining proposed Modulated Elliptical SpiralFC with the star operation to capture spatial relationships and efficiently follow complex handwriting stroke trajectories, while a Spiral-Modulated discriminator is introduced for multi-domain flaws detection. Additionally, we introduce a Sobel-Regularized Edge Reconstruction Loss that provides edge guidance, ensuring every character remains clear and legible. Evaluations on the English and Vietnamese datasets demonstrate that SpiS-GAN significantly outperforms current state-of-the-art models. The generated images are highly authentic, accurately preserve the original writer's style across languages, and successfully lower error rates when training downstream HTR systems.

Problem

• handwriting synthesis
• cursive handwriting
• stroke boundaries
• structural details
• high-resolution synthesis

Innovation

• Spiral-Modulated Synthesis
• Star Operation
• Modulated Elliptical SpiralFC
• Sobel-Regularized Edge Loss
• Handwriting Generation