Search papers, labs, and topics across Lattice.
This paper introduces SpiS-GAN, a novel handwriting synthesis framework that addresses key limitations in existing models by utilizing Star-Spiral Blocks and a Spiral-Modulated discriminator to enhance the generation of cursive handwriting. The proposed approach effectively captures complex stroke trajectories and incorporates edge guidance through a Sobel-Regularized Edge Reconstruction Loss, resulting in clearer and more authentic handwriting samples. Evaluations on English and Vietnamese datasets reveal that SpiS-GAN outperforms state-of-the-art models, significantly reducing error rates in downstream handwriting recognition tasks.
SpiS-GAN generates highly authentic handwriting that preserves original styles while significantly improving recognition accuracy across languages.
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.
