Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
FlowExtract is introduced as a pipeline to extract directed graphs representing procedural knowledge from maintenance flowcharts by decoupling node detection and connectivity reconstruction. Node detection and text extraction are performed using YOLOv8 and EasyOCR, while a novel edge detection method analyzes arrowhead orientations and traces connecting lines backward to source nodes. Results on industrial troubleshooting guides show FlowExtract achieves high node detection accuracy and significantly outperforms vision-language model baselines in edge extraction.
Free your maintenance flowcharts from static PDFs: FlowExtract offers a practical pipeline for turning visual diagrams into queryable knowledge graphs.
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.