A Symbol Recognition System for Single-Line Diagrams Developed Using a Deep-Learning Approach

• Main Author: Bhanbhro H.
• Other Authors: Mahidol University
• Format: Article
• Published: 2023
• Subjects: Chemical Engineering
• Online Access: https://repository.li.mahidol.ac.th/handle/123456789/88836

Featured Application: The present study is among the first research efforts to generate augmented datasets of complex single-line diagrams to detect symbols using deep-learning-based algorithms. The work determines the impacts of augmented datasets on model performance and indicates future directions in the field of engineering drawings. In numerous electrical power distribution systems and other engineering contexts, single-line diagrams (SLDs) are frequently used. The importance of digitizing these images is growing. This is primarily because better engineering practices are required in areas such as equipment maintenance, asset management, safety, and others. Processing and analyzing these drawings, however, is a difficult job. With enough annotated training data, deep neural networks perform better in many object detection applications. Based on deep-learning techniques, a dataset can be used to assess the overall quality of a visual system. Unfortunately, there are no such datasets for single-line diagrams available to the general research community. To augment real image datasets, generative adversarial networks (GANs) can be used to create a variety of more realistic training images. The goal of this study was to explain how deep-convolutional-GAN- (DCGAN) and least-squares-GAN- (LSGAN) generated images are evaluated for quality. In order to improve the datasets and confirm the effectiveness of synthetic datasets, our work blended synthetic images with actual images. Additionally, we added synthetic images to the original picture collection to prepare an augmented dataset for symbol detection. In this scenario, we employed You Look Only Once (YOLO) V5, one of the versions of YOLO. The recognition performance was improved, reaching an accuracy of 95% with YOLO V5, after combining the actual images with the synthetic images created by the DCGAN and LSGAN. By incorporating synthetic samples into the dataset, the overall quality of the training data was improved, and the learning process for the model became simpler. Furthermore, the proposed method significantly improved symbol detection in SLDs, according to the findings of the experiments.