Fuzzy-Geometric Branch-Point Modeling for Structure-Aware Augmentation of Handwritten Chinese Characters

2026-06-17

AI Summary

This study addresses performance bottlenecks in handwritten Chinese character recognition caused by data scarcity and structural distortion by proposing a Fuzzy Geometry-driven Structure-Aware augmentation framework (FGSA). The method introduces fuzzy geometry into character augmentation for the first time, modeling branch points in the skeleton space as fuzzy sets to construct an adaptively optimizable membership field. Coupled with an unsupervised proxy objective, FGSA enables annotation-free stroke disentanglement and structure-preserving sample synthesis. Key contributions include a parameterized Bézier curve reconstruction scheme, a multi-strategy perturbation mechanism, and the creation of LZUSig—a large-scale dataset tailored to fine-grained structural degradation. Extensive experiments on CASIA-HWDB1.1, ChiSig, and LZUSig demonstrate significant reductions in word-level error rates, outperforming state-of-the-art methods while achieving a robust balance among augmentation diversity, structural fidelity, and discriminative feature preservation.

Abstract

Data scarcity and structural distortion significantly limit handwriting recognition in high-security authentication. Existing augmentation methods often cause topological and morphological damage, particularly when processing complex Chinese characters where stroke intersections, ligatures, and sharp turns render traditional branch-point detection unreliable. To address this, this paper proposes a fuzzy geometry-driven structure-aware (FGSA) augmentation framework. We model branch points as fuzzy sets within the skeleton space, constructing a continuous branch-point membership field by integrating topological neighborhood evidence with direction field divergence. This membership field is adaptively optimized via an unsupervised surrogate objective, enabling robust stroke decoupling without manual annotation. Finally, kinematically-aligned samples are synthesized through parameterized cubic Bézier reconstruction and multi-strategy perturbations, ensuring a balance between structural fidelity and sample diversity. Moreover, we establish LZUSig, a large-scale, highly challenging dataset specifically dedicated to fine-grained structural degradation in Chinese handwritten signatures. Extensive experiments on CASIA-HWDB1.1, ChiSig, and LZUSig demonstrate that FGSA significantly reduces the word-level error rate ($Δ$WER), achieving optimal recognition gains over the compared baselines. More importantly, it strikes a robust trade-off among task gain, structural fidelity, and discriminative feature preservation, offering a highly controllable solution for handwriting augmentation.

Problem

• handwriting recognition
• data augmentation
• structural distortion
• branch-point detection
• Chinese characters

Innovation

• fuzzy geometry
• structure-aware augmentation
• branch-point modeling
• skeleton-based representation
• handwritten Chinese character