Automatic raster engineering drawing digitisation for legacy parts towards advanced manufacturing

Mechanical engineering drawings are commonly used in multiple industries, carrying essential information about the design and technical specifications of the parts they define. With large industry sectors shifting to advanced manufacturing processes and technologies such as additive manufacturing, arises the need for systems checking whether legacy parts described by engineering drawings can be optimally produced. To this end, the digitisation of engineering drawings has become the key issue for the following computer-aided engineering tasks towards advanced manufacturing. This paper presents a pipeline for information extraction in raster mechanical engineering drawings through a combination of traditional and deep-learning-based computer vision techniques. Object detection and text recognition techniques are implemented to achieve automatic interpretation of engineering drawings. A dataset of 217 industrial engineering drawings is created to evaluate the proposed method. Different types of information within engineering drawings, including information blocks, views, dimensions, and Geometric Dimensioning and Tolerancing (GD&T) information, are extracted automatically. A case study of engineering drawing digitisation for a complex part is presented to illustrate the effectiveness of the proposed method.