将流程图图片转为可编辑的Mermaid代码，支持自然语言修改。
Flowchart2Mermaid: A Vision-Language Model Powered System for Converting Flowcharts into Editable Diagram Code
- 用视觉语言模型识别流程图并生成结构化Mermaid代码
- 支持文本编辑、拖拽节点和自然语言指令实时修改
- 提供结构、流程、语法和完整性评估指标
流程图是表达流程的常用工具，但通常以静态图像形式共享，难以编辑或复用。我们提出Flowchart2Mermaid，一个轻量级网页系统，利用详细系统提示和视觉语言模型，将流程图图像转换为可编辑的Mermaid.js代码（一种用于可视化工作流的标记语言）。该界面支持混合协同优化：通过内联文本编辑、拖拽节点插入以及由集成AI助手解析的自然语言命令进行交互。与以往图像转图表工具不同，本方法生成结构化的、可版本控制的文本表示，且始终与渲染图保持同步。我们还引入评估指标，用于衡量多种模型在结构准确性、流程正确性、语法有效性及完整性方面的表现。
原文摘要 · Abstract (English)
Flowcharts are common tools for communicating processes but are often shared as static images that cannot be easily edited or reused. We present Flowchart2Mermaid, a lightweight web system that converts flowchart images into editable Mermaid.js code which is a markup language for visual workflows, using a detailed system prompt and vision-language models. The interface supports mixed-initiative refinement through inline text editing, drag-and-drop node insertion, and natural-language commands interpreted by an integrated AI assistant. Unlike prior image-to-diagram tools, our approach produces a structured, version-controllable textual representation that remains synchronized with the rendered diagram. We further introduce evaluation metrics to assess structural accuracy, flow correctness, syntax validity, and completeness across multiple models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。