轻量级模型提升韩文字符识别准确率与速度
A Lightweight Multi-Module Fusion Approach for Korean Character Recognition
- 融合笔画注意力与动态上下文编码，增强特征提取
- 在多个基准上达到顶尖准确率，推理速度快30%以上
- 适合实时和边缘设备部署，尤其适用于移动端
光学字符识别（OCR）在文档处理、车牌识别和智能监控中至关重要。然而，现有模型在真实场景中常因文本布局不规则、图像质量差、字符变化大及计算成本高而表现不佳。本文提出SDA-Net（笔画敏感注意力与动态上下文编码网络），一种轻量高效架构，专为鲁棒的单字符识别设计。该模型包含：(1) 双注意力机制，提升笔画级与空间特征提取能力；(2) 动态上下文编码模块，通过可学习门控机制自适应优化语义信息；(3) 类U-Net的特征融合策略，有效结合低层与高层特征；(4) 高度优化的轻量化主干网络，显著降低内存与计算开销。实验表明，SDA-Net在多个挑战性OCR基准上达到当前最优准确率，且推理速度大幅提升，非常适合实时与边缘端OCR系统部署。
原文摘要 · Abstract (English)
Optical Character Recognition (OCR) is essential in applications such as document processing, license plate recognition, and intelligent surveillance. However, existing OCR models often underperform in real-world scenarios due to irregular text layouts, poor image quality, character variability, and high computational costs. This paper introduces SDA-Net (Stroke-Sensitive Attention and Dynamic Context Encoding Network), a lightweight and efficient architecture designed for robust single-character recognition. SDA-Net incorporates: (1) a Dual Attention Mechanism to enhance stroke-level and spatial feature extraction; (2) a Dynamic Context Encoding module that adaptively refines semantic information using a learnable gating mechanism; (3) a U-Net-inspired Feature Fusion Strategy for combining low-level and high-level features; and (4) a highly optimized lightweight backbone that reduces memory and computational demands. Experimental results show that SDA-Net achieves state-of-the-art accuracy on challenging OCR benchmarks, with significantly faster inference, making it well-suited for deployment in real-time and edge-based OCR systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。