Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.06770 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915923580944384 |
|---|---|
| author | de Avalle, Guillermo Gil Maruster, Laura Sloot, Eric Emmanouilidis, Christos |
| author_facet | de Avalle, Guillermo Gil Maruster, Laura Sloot, Eric Emmanouilidis, Christos |
| contents | Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowledge essential for asset lifecycle management, yet inaccessible to modern operator support systems. Vision-language models, the dominant paradigm for image understanding, struggle to reconstruct connection topology from such diagrams. We present FlowExtract, a pipeline for extracting directed graphs from ISO 5807-standardized flowcharts. The system separates element detection from connectivity reconstruction, using YOLOv8 and EasyOCR for standard domain-aligned node detection and text extraction, combined with a novel edge detection method that analyzes arrowhead orientations and traces connecting lines backward to source nodes. Evaluated on industrial troubleshooting guides, FlowExtract achieves very high node detection and substantially outperforms vision-language model baselines on edge extraction, offering organizations a practical path toward queryable procedural knowledge representations. The implementation is available athttps://github.com/guille-gil/FlowExtract. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06770 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts de Avalle, Guillermo Gil Maruster, Laura Sloot, Eric Emmanouilidis, Christos Computer Vision and Pattern Recognition Artificial Intelligence Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowledge essential for asset lifecycle management, yet inaccessible to modern operator support systems. Vision-language models, the dominant paradigm for image understanding, struggle to reconstruct connection topology from such diagrams. We present FlowExtract, a pipeline for extracting directed graphs from ISO 5807-standardized flowcharts. The system separates element detection from connectivity reconstruction, using YOLOv8 and EasyOCR for standard domain-aligned node detection and text extraction, combined with a novel edge detection method that analyzes arrowhead orientations and traces connecting lines backward to source nodes. Evaluated on industrial troubleshooting guides, FlowExtract achieves very high node detection and substantially outperforms vision-language model baselines on edge extraction, offering organizations a practical path toward queryable procedural knowledge representations. The implementation is available athttps://github.com/guille-gil/FlowExtract. |
| title | FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06770 |