Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach
CoRR(2024)
摘要
Flowcharts and mind maps, collectively known as flowmind, are vital in daily
activities, with hand-drawn versions facilitating real-time collaboration.
However, there's a growing need to digitize them for efficient processing.
Automated conversion methods are essential to overcome manual conversion
challenges. Existing sketch recognition methods face limitations in practical
situations, being field-specific and lacking digital conversion steps. Our
paper introduces the Flowmind2digital method and hdFlowmind dataset to address
these challenges. Flowmind2digital, utilizing neural networks and keypoint
detection, achieves a record 87.3
methods by 11.9
across 22 scenarios, outperforms existing datasets. Additionally, our
experiments emphasize the importance of simple graphics, enhancing accuracy by
9.3
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要