Component Segmentation of Engineering Drawings Using Graph Convolutional Networks

Such drawings encode the topological information, dimensions, and manufacturing requirements of a product in a unified and standard form, which can then be utilized in various engineering applications including content-based part indexing (Fonseca et al., 2005; Kasimov et al., 2015), cost estimation (Sajadfar and Ma, 2015), and process planning (Kulkarni et al., 2000). Although the underlying designs are commonly created in a vector format through digital design tools, a raster drawing is more frequently used by manufacturers due to the ease of information exchange and quality assurance. According to a survey of Japan's manufacturing industry (Mitsubishi UFJ Research & Consulting Co., 2019), 84% of the customers use 2D raster-based drawings such as PDF, paper, or fax format when placing an order for manufacturing, which results in a major impediment in the automation of the aforementioned applications due to the need for human involvement in interpreting these drawings. For a modern online platform of part manufacturing, clients often upload their designs in raster image format for better quality assurance and IP protection since the information in image drawings is noneditable. Unlike a vector format, which enables trivial digital access to all stored information through a script file, raster drawings usually require manual inspection by technicians to extract the information required for quotation and manufacturing. The inspection process includes the identification of the part shape, dimensions, and manufacturing requirements. Here, we focus on the problem of semantic segmentation of the components in raster drawings. Common mechanical engineering components consist of straight lines, arcs, and circles. Our goal is to develop an automated data-driven framework that learns to distinguish between contour shapes, dimension sets, and text at the component level.