TY - JOUR
T1 - Tolerance Information Extraction for Mechanical Engineering Drawings – A Digital Image Processing and Deep Learning-based Model
AU - Xu, Yuanping
AU - Zhang, Chaolong
AU - Xu, Zhijie
AU - Kong, Chao
AU - Tang, Dan
AU - Deng, Xin
AU - Li, Tukun
AU - Jin, Jin
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/6
Y1 - 2024/6
N2 - Mechanical engineering drawings (MEDs) accompany a product lifecycle from conceptional design to final production. The digitisation of MEDs has become increasingly important due to demands for data authenticity, intellectual property protection, efficient data storage and communication, and compliance with data integrity and security regulations. Unlike CAD-based engineering design software, legacy MEDs are often manually drawn or contain manually labeled specifications on blueprints. A notable gap exists in the automated process pipeline of modern Computer-Aided Tolerance (CAT) software, particularly in integrating Geometrical Tolerance Specification Callouts (GTSC) on MEDs. This study proposes an integrated model based on digital image processing and deep learning, which combines character (symbol, text and number) localization, segmentation, and recognition to intelligently identify and read GTSCs on MEDs. The focus of this work is on image filtering, GTSC block localization and tilt correction, multiple lines and character segmentation, and semantic recognition. Experiment results demonstrate that this innovative technique effectively automates the labor-intensive process of reading and registering GTSC with a precision performance that meets industry benchmarks.
AB - Mechanical engineering drawings (MEDs) accompany a product lifecycle from conceptional design to final production. The digitisation of MEDs has become increasingly important due to demands for data authenticity, intellectual property protection, efficient data storage and communication, and compliance with data integrity and security regulations. Unlike CAD-based engineering design software, legacy MEDs are often manually drawn or contain manually labeled specifications on blueprints. A notable gap exists in the automated process pipeline of modern Computer-Aided Tolerance (CAT) software, particularly in integrating Geometrical Tolerance Specification Callouts (GTSC) on MEDs. This study proposes an integrated model based on digital image processing and deep learning, which combines character (symbol, text and number) localization, segmentation, and recognition to intelligently identify and read GTSCs on MEDs. The focus of this work is on image filtering, GTSC block localization and tilt correction, multiple lines and character segmentation, and semantic recognition. Experiment results demonstrate that this innovative technique effectively automates the labor-intensive process of reading and registering GTSC with a precision performance that meets industry benchmarks.
KW - Character extraction
KW - Character recognition
KW - Deep learning
KW - Digitalization
KW - Geometrical tolerance specification callouts
KW - GTSC blocks
KW - Mechanical engineering drawings
UR - http://www.scopus.com/inward/record.url?scp=85186111848&partnerID=8YFLogxK
U2 - 10.1016/j.cirpj.2024.01.013
DO - 10.1016/j.cirpj.2024.01.013
M3 - Article
AN - SCOPUS:85186111848
SN - 1755-5817
VL - 50
SP - 55
EP - 64
JO - CIRP Journal of Manufacturing Science and Technology
JF - CIRP Journal of Manufacturing Science and Technology
ER -