Automatic Detection and Classification of Symbols in Engineering Drawings
This addresses the need for automated analysis of engineering drawings in industries like design validation, but it appears incremental as it builds on existing deep learning techniques.
The paper tackles the problem of automatically detecting and classifying symbols in engineering drawings using deep neural networks, achieving a method that works on unseen templates without additional training.
A method of finding and classifying various components and objects in a design diagram, drawing, or planning layout is proposed. The method automatically finds the objects present in a legend table and finds their position, count and related information with the help of multiple deep neural networks. The method is pre-trained on several drawings or design templates to learn the feature set that may help in representing the new templates. For a template not seen before, it does not require any training with template dataset. The proposed method may be useful in multiple industry applications such as design validation, object count, connectivity of components, etc. The method is generic and domain independent.