提出轻量旋转检测方法，提升文档OCR的准确率
Seeing Straight: Document Orientation Detection for Efficient OCR
- 基于Phi-3.5-Vision视觉编码器，结合动态裁剪实现快速旋转分类
- 在双语数据集上分别达到96%和92%的旋转识别准确率
- 可显著提升闭源与开源OCR模型性能，适合实际文档处理场景
尽管文档理解技术取得显著进展，但在真实场景中确定扫描或拍摄文档的正确方向仍是关键预处理步骤。准确的旋转校正对下游任务如光学字符识别（OCR）至关重要，因用户操作失误常导致相机基线方向错误。本文首次提出OCR-Rotation-Bench（ORB）基准，包含两个部分：(i) ORB-En，由旋转变换的结构化和自由格式英文OCR数据集构建；(ii) ORB-Indic，涵盖11种印地语系中低资源语言的新型多语言数据集。我们还设计了一种快速、鲁棒且轻量的旋转分类流水线，基于Phi-3.5-Vision视觉编码器并采用动态图像裁剪，专为4类旋转任务独立微调。该方法在两个数据集上分别实现96%和92%的准确率。此外，实验表明该模块在模拟真实场景下显著提升OCR性能：闭源模型最高提升14%，开源模型最高提升4倍。
原文摘要 · Abstract (English)
Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real world settings. Accurate rotation correction is essential for enhancing the performance of downstream tasks such as Optical Character Recognition (OCR) where misalignment commonly arises due to user errors, particularly incorrect base orientations of the camera during capture. In this study, we first introduce OCR-Rotation-Bench (ORB), a new benchmark for evaluating OCR robustness to image rotations, comprising (i) ORB-En, built from rotation-transformed structured and free-form English OCR datasets, and (ii) ORB-Indic, a novel multilingual set spanning 11 Indic mid to low-resource languages. We also present a fast, robust and lightweight rotation classification pipeline built on the vision encoder of Phi-3.5-Vision model with dynamic image cropping, fine-tuned specifically for 4-class rotation task in a standalone fashion. Our method achieves near-perfect 96% and 92% accuracy on identifying the rotations respectively on both the datasets. Beyond classification, we demonstrate the critical role of our module in boosting OCR performance: closed-source (up to 14%) and open-weights models (up to 4x) in the simulated real-world setting.
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。