Few-Shot Symbol Detection in Engineering Drawings
Recently, there has been significant interest in digitizing engineering drawings due to their complexity and practical benefits. Symbol digitization, a critical aspect in this field, is challenging as utilizing Deep Learning-based methods to recognize symbols of interest requires a large number of t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2024.2406712 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255222685827072 |
|---|---|
| author | Laura Jamieson Eyad Elyan Carlos Francisco Moreno-García |
| author_facet | Laura Jamieson Eyad Elyan Carlos Francisco Moreno-García |
| author_sort | Laura Jamieson |
| collection | DOAJ |
| description | Recently, there has been significant interest in digitizing engineering drawings due to their complexity and practical benefits. Symbol digitization, a critical aspect in this field, is challenging as utilizing Deep Learning-based methods to recognize symbols of interest requires a large number of training instances for each class of symbols. Acquiring and annotating sufficient diagrams is difficult due to concerns about confidentiality and availability. The conventional manual annotation process is time-consuming, costly, and prone to human error. Additionally, obtaining an adequate number of samples for rare classes proves to be exceptionally challenging. This paper introduces a few-shot framework to address these challenges. Several experiments with fewer than ten, and sometimes just one, training instance per class using complex engineering drawings from industry sources were carried out. The results suggest that our method not only significantly improves symbol detection performance compared to other state-of-the-art methods but also decreases the necessary number of training instances. |
| format | Article |
| id | doaj-art-ae043d01cb374191a37fb5b2a0a12b46 |
| institution | OA Journals |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-ae043d01cb374191a37fb5b2a0a12b462025-08-20T01:56:56ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2406712Few-Shot Symbol Detection in Engineering DrawingsLaura Jamieson0Eyad Elyan1Carlos Francisco Moreno-García2School of Computing, Robert Gordon University, Aberdeen, Scotland, UKSchool of Computing, Robert Gordon University, Aberdeen, Scotland, UKSchool of Computing, Robert Gordon University, Aberdeen, Scotland, UKRecently, there has been significant interest in digitizing engineering drawings due to their complexity and practical benefits. Symbol digitization, a critical aspect in this field, is challenging as utilizing Deep Learning-based methods to recognize symbols of interest requires a large number of training instances for each class of symbols. Acquiring and annotating sufficient diagrams is difficult due to concerns about confidentiality and availability. The conventional manual annotation process is time-consuming, costly, and prone to human error. Additionally, obtaining an adequate number of samples for rare classes proves to be exceptionally challenging. This paper introduces a few-shot framework to address these challenges. Several experiments with fewer than ten, and sometimes just one, training instance per class using complex engineering drawings from industry sources were carried out. The results suggest that our method not only significantly improves symbol detection performance compared to other state-of-the-art methods but also decreases the necessary number of training instances.https://www.tandfonline.com/doi/10.1080/08839514.2024.2406712 |
| spellingShingle | Laura Jamieson Eyad Elyan Carlos Francisco Moreno-García Few-Shot Symbol Detection in Engineering Drawings Applied Artificial Intelligence |
| title | Few-Shot Symbol Detection in Engineering Drawings |
| title_full | Few-Shot Symbol Detection in Engineering Drawings |
| title_fullStr | Few-Shot Symbol Detection in Engineering Drawings |
| title_full_unstemmed | Few-Shot Symbol Detection in Engineering Drawings |
| title_short | Few-Shot Symbol Detection in Engineering Drawings |
| title_sort | few shot symbol detection in engineering drawings |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2024.2406712 |
| work_keys_str_mv | AT laurajamieson fewshotsymboldetectioninengineeringdrawings AT eyadelyan fewshotsymboldetectioninengineeringdrawings AT carlosfranciscomorenogarcia fewshotsymboldetectioninengineeringdrawings |