Research Paper: Pattern Recognition for Technical Drawings

 

Abstract

In this digital transformation era, the demand for automatic pattern extraction from printed materials has never been higher, making it one of the most eminent problems nowadays. In this paper, we propose a solution for pattern recognition in highly complex technical drawings, which is then applied to solve the problem presented by the Toyota Project. Our solution is a pipeline system that includes two phases: : (1) detecting the objects that contain the patterns of interest, and (2) performing character recognition on the objects if they are text patterns. By utilizing state-of-the-art models and proposing several improvements to the methods of both phases, our experiments on nearly five thousand real technical drawings show promising results and the capability to reduce manual labeling effort to a great extent.

 

Keywords – digital transformation, object detection, optical character recognition