重庆邮电大学学报（自然科学版）2025，Vol.37Issue(5)：696-707,12.DOI:10.3979/j.issn.1673-825X.202408260226
深度学习方法在工程图纸标识定位与识别中的应用研究
Research on the application of deep learning methods in identification localization and recognition of engineering drawings
摘要
Abstract
The localization and recognition of key symbols in engineering drawings have long been essential applications in computer vision.Compared with traditional methods,deep learning-based text detection approaches offer higher detection efficiency and accuracy.It is therefore necessary to apply existing text detection algorithms to engineering drawing recogni-tion tasks.This paper proposes a deep learning-based method for the localization and recognition of key symbols in engineer-ing drawings,focusing on the detection and recognition of index symbols and dimension symbols.For index symbol localiza-tion,the drawings are cropped to a uniform size,and non-maximum suppression is used to remove redundant candidate bo-xes.For dimension symbol localization,a complete detection is performed on the masked drawings,and the intersection-o-ver-union between each detected box and index symbol location is calculated to filter out partial data.Experimental results demonstrate that the proposed method achieves high precision and recall in both the localization and recognition of index and dimension symbols in engineering drawings.关键词
工程图纸/目标检测/字符识别/深度学习Key words
engineering drawings/object detection/character recognition/deep learning分类
计算机与自动化引用本文复制引用
肖鑫,陈青松,吴思远,胡瑞..深度学习方法在工程图纸标识定位与识别中的应用研究[J].重庆邮电大学学报（自然科学版）,2025,37(5):696-707,12.基金项目
国家自然科学基金项目(62302074) （62302074）
重庆市教委科学技术研究项目(KJQN202300631)National Natural Science Foundation of China(62302074) （KJQN202300631）
Science and Technology Research Program of Chongqing Municipal Education Commission(KJQN202300631) （KJQN202300631）
