Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach
The digitalization of engineering drawings is a pivotal step toward automating and improving the efficiency of product design and manufacturing systems (PDMSs). This study presents eDOCr2, a framework that combines traditional OCR and image processing to extract structured information from mechanica...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/3/254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850204454179045376 |
|---|---|
| author | Javier Villena Toro Mehdi Tarkian |
| author_facet | Javier Villena Toro Mehdi Tarkian |
| author_sort | Javier Villena Toro |
| collection | DOAJ |
| description | The digitalization of engineering drawings is a pivotal step toward automating and improving the efficiency of product design and manufacturing systems (PDMSs). This study presents eDOCr2, a framework that combines traditional OCR and image processing to extract structured information from mechanical drawings. It segments drawings into key elements—such as information blocks, dimensions, and feature control frames—achieving a text recall of 93.75% and a character error rate (CER) below 1% in a benchmark with drawings from different sources. To improve semantic understanding and reasoning, eDOCr2 integrates Vision Language models (Qwen2-VL-7B and GPT-4o) after segmentation to verify, filter, or retrieve information. This integration enables PDMS applications such as automated design validation, quality control, or manufacturing assessment. The code is available on Github. |
| format | Article |
| id | doaj-art-bd8a809e3b5c4c718c3e3dd8cbbc030d |
| institution | OA Journals |
| issn | 2075-1702 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-bd8a809e3b5c4c718c3e3dd8cbbc030d2025-08-20T02:11:17ZengMDPI AGMachines2075-17022025-03-0113325410.3390/machines13030254Optimizing Text Recognition in Mechanical Drawings: A Comprehensive ApproachJavier Villena Toro0Mehdi Tarkian1Department of Management and Engineering, Linköping University, SE-581 83 Linköping, SwedenDepartment of Management and Engineering, Linköping University, SE-581 83 Linköping, SwedenThe digitalization of engineering drawings is a pivotal step toward automating and improving the efficiency of product design and manufacturing systems (PDMSs). This study presents eDOCr2, a framework that combines traditional OCR and image processing to extract structured information from mechanical drawings. It segments drawings into key elements—such as information blocks, dimensions, and feature control frames—achieving a text recall of 93.75% and a character error rate (CER) below 1% in a benchmark with drawings from different sources. To improve semantic understanding and reasoning, eDOCr2 integrates Vision Language models (Qwen2-VL-7B and GPT-4o) after segmentation to verify, filter, or retrieve information. This integration enables PDMS applications such as automated design validation, quality control, or manufacturing assessment. The code is available on Github.https://www.mdpi.com/2075-1702/13/3/254mechanical drawingsoptical character recognitionintelligent document processingquality controlvision language models |
| spellingShingle | Javier Villena Toro Mehdi Tarkian Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach Machines mechanical drawings optical character recognition intelligent document processing quality control vision language models |
| title | Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach |
| title_full | Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach |
| title_fullStr | Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach |
| title_full_unstemmed | Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach |
| title_short | Optimizing Text Recognition in Mechanical Drawings: A Comprehensive Approach |
| title_sort | optimizing text recognition in mechanical drawings a comprehensive approach |
| topic | mechanical drawings optical character recognition intelligent document processing quality control vision language models |
| url | https://www.mdpi.com/2075-1702/13/3/254 |
| work_keys_str_mv | AT javiervillenatoro optimizingtextrecognitioninmechanicaldrawingsacomprehensiveapproach AT mehditarkian optimizingtextrecognitioninmechanicaldrawingsacomprehensiveapproach |