基于微调文档理解Transformer的工程图纸自动解析以实现结构化信息提取
Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer
AI总结：
针对工程图纸信息人工提取低效、传统OCR效果不佳的问题，提出融合YOLOv11定向边界框检测与微调Donut的混合深度学习框架，在自制标注数据集上实现9类信息的结构化提取，单一模型性能更优，可助力高精度制造行业降本增效。
摘要：
从2D工程图纸中准确提取关键信息对高精度制造至关重要。人工提取速度慢、劳动强度大，而传统光学字符识别（OCR）技术往往难以应对复杂布局和重叠符号，输出结果为非结构化形式。为解决这些挑战，本文提出一种新型混合深度学习框架，通过将定向边界框（OBB）检测模型与基于Transformer的文档解析模型（Donut）相结合，实现结构化信息提取。研究使用内部标注数据集训练YOLOv11，用于检测9个关键类别：几何尺寸与公差（GD&T）、通用公差、尺寸标注、材料、注释、半径、表面粗糙度、螺纹以及标题栏。将检测到的OBB裁剪为图像并标注，用于微调Donut以生成结构化JSON输出。微调策略包括在所有类别上训练的单一模型，以及针对特定类别的模型。结果表明，单一模型在所有评估指标上始终优于特定类别模型，实现了更高的精确率（GD&T为94.77%）、召回率（大多数类别为100%）和F1分数（97.3%），同时降低了幻觉率（5.23%）。该框架提高了准确性，减少了人工工作量，支持在精度驱动的行业中规模化部署。
英文摘要：
Accurate extraction of key information from 2D engineering drawings is crucial for high-precision manufacturing. Manual extraction is slow and labor-intensive, while traditional Optical Character Recognition (OCR) techniques often struggle with complex layouts and overlapping symbols, resulting in unstructured outputs. To address these challenges, this paper proposes a novel hybrid deep learning framework for structured information extraction by integrating an Oriented Bounding Box (OBB) detection model with a transformer-based document parsing model (Donut). An in-house annotated dataset is used to train YOLOv11 for detecting nine key categories: Geometric Dimensioning and Tolerancing (GD&T), General Tolerances, Measures, Materials, Notes, Radii, Surface Roughness, Threads, and Title Blocks. Detected OBBs are cropped into images and labeled to fine-tune Donut for structured JSON output. Fine-tuning strategies include a single model trained across all categories and category-specific models. Results show that the single model consistently outperforms category-specific ones across all evaluation metrics, achieving higher precision (94.77% for GD&T), recall (100% for most categories), and F1 score (97.3%), while reducing hallucinations (5.23%). The proposed framework improves accuracy, reduces manual effort, and supports scalable deployment in precision-driven industries.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
