EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering
2026-05-26 • Software Engineering
Software EngineeringArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem that Vision Language Models (VLMs) often miss important structural details when converting flowchart images into usable machine-readable models. They propose EdgeFlow, which adds a special edge map to help VLMs better understand the flowchart's layout without needing extra training or fine-tuning. Testing on a real-world dataset, EdgeFlow significantly improved accuracy in identifying flowchart nodes and connections. However, it did not show improvements on a synthetic benchmark, suggesting that diverse, real-life data is important for future evaluations.
FlowchartsVision Language ModelsCanny edge detectionMachine-readable modelsMermaid notationRequirements EngineeringNode-level F1Edge-level F1Model-based testingDataset evaluation
Authors
Zhifei Dou, Shabnam Hassani, Ou Wei
Abstract
Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE activities, yet, when directly applied to flowchart conversion, they often fail on topology-critical visual details. To address this, we propose EdgeFlow that augments a VLM's original input with a deterministically extracted Canny edge map-acting as a structural prior-to improve flowchart-to-Mermaid conversion, without requiring annotated training data or domain-specific model fine-tuning. We evaluate EdgeFlow on IndusReqFlow, a dataset sourced from real-world requirements. Compared with off-the-shelf VLMs, EdgeFlow improves node-level F1 by 17.39 percentage points and edge-level F1 by 16.94 percentage points. At the path level, EdgeFlow improves path F1 by 11.06 percentage points, enabling better support for model-based testing. These results demonstrate that EdgeFlow provides a practical, training-free means to improve topology-preserving flowchart-to-Mermaid conversion for industrial RE. Cross-dataset evaluation results on a public synthetic benchmark show no significant improvement; this highlights the need for diverse benchmarks incorporating industrial data for the comprehensive evaluation of future VLM-based RE tools.