Abstract
Optical character recognition remains critical infrastructure for document digitization, yet state-of-the-art performance is often restricted to well-resourced institutions by prohibitive computational barriers. End-to-end transformer architectures achieve strong accuracy but demand hundreds of GPU hours for domain adaptation, limiting accessibility for practitioners and digital humanities scholars. We present a modular detection-and-correction framework that achieves near-SOTA accuracy with single-GPU training. Our approach decouples lightweight visual character detection (domain-agnostic) from domain-specific linguistic correction using pretrained sequence models including T5, ByT5, and BART. By training the correctors entirely on synthetic noise, we enable annotation-free domain adaptation without requiring labeled target images. Evaluating across modern clean handwriting, cursive script, and historical documents, we identify a critical "Pareto frontier" in architecture selection: T5-Base excels on modern text with standard vocabulary, whereas ByT5-Base dominates on historical documents by reconstructing archaic spellings at the byte level. Our results demonstrate that this decoupled paradigm matches end-to-end transformer accuracy while reducing compute by approximately 95%, establishing a viable, resource-efficient alternative to monolithic OCR architectures.
Abstract (translated)
光学字符识别仍是文档数字化的重要基础设施，然而最先进的性能往往因高昂的计算门槛而局限于资源充足的机构。端到端Transformer架构虽能实现高精度，但领域自适应需消耗数百GPU小时，限制了实践者与数字人文研究者的使用。我们提出一种模块化的检测-校正框架，仅用单GPU训练即可实现接近SOTA的准确率。该方法将轻量级的视觉字符检测（领域无关）与基于预训练序列模型（包括T5、ByT5和BART）的领域特定语言校正解耦。通过完全在合成噪声数据上训练校正器，我们实现了无需标注目标图像的免标注领域自适应。在现代清晰手写体、草书及历史文档的跨领域评估中，我们识别出架构选择的关键"帕累托前沿"：T5-Base模型在标准词汇的现代文本上表现卓越，而ByT5-Base则凭借字节级重建古旧拼写，在历史文档中占据优势。结果表明，这种解耦范式在匹配端到端Transformer精度的同时，将计算量降低约95%，为整体式OCR架构提供了可行且资源高效的替代方案。
URL
https://arxiv.org/abs/2603.28028
