# Unified Line and Paragraph Detection by Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2203.09638 · HTML: https://mlsanity.com/paper/2203.09638/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 17 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 16 of 16)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2003.07493/) (2020)
- [Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2107.12664/) (2021)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [A Two-Stage Method for Text Line Detection in Historical Documents](https://mlsanity.com/paper/1802.03345/) (2018)
- [A Scalable Handwritten Text Recognition System](https://mlsanity.com/paper/1904.09150/) (2019)
- [ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction](https://mlsanity.com/paper/2106.10786/) (2021)
- [ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks](https://mlsanity.com/paper/2003.06999/) (2020)
- [docExtractor: An off-the-shelf historical document element extraction](https://mlsanity.com/paper/2012.08191/) (2020)
- [Page Layout Analysis System for Unconstrained Historic Documents](https://mlsanity.com/paper/2102.11838/) (2021)
- [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://mlsanity.com/paper/2101.12741/) (2021)
- [Text Flow: A Unified Text Detection System in Natural Scene Images](https://mlsanity.com/paper/1604.06877/) (2016)
- [Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings](https://mlsanity.com/paper/2010.01305/) (2020)

## Built on by (most cited first, 7 of 7)

- [ICDAR 2023 Competition on Hierarchical Text Detection and Recognition](https://mlsanity.com/paper/2305.09750/) (2023)
- [Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis](https://mlsanity.com/paper/2401.11874/) (2024)
- [DLAFormer: An End-to-End Transformer For Document Layout Analysis](https://mlsanity.com/paper/2405.11757/) (2024)
- [Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation](https://mlsanity.com/paper/2305.02577/) (2023)
- [PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis](https://mlsanity.com/paper/2304.11810/) (2023)
- [Dynamic Relation Transformer for Contextual Text Block Detection](https://mlsanity.com/paper/2401.09232/) (2024)
- [Block-level Text Spotting with LLMs](https://mlsanity.com/paper/2406.13208/) (2024)

## Abstract (arXiv)

We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem. Given a set of text detection boxes that roughly correspond to words, a text line is a cluster of boxes and a paragraph is a cluster of lines. These clusters form a two-level tree that represents a major part of the layout of a document. We use a graph convolutional network to predict the relations between text detection boxes and then build both levels of clusters from these predictions. Experimentally, we demonstrate that the unified approach can be highly efficient while still achieving state-of-the-art quality for detecting paragraphs in public benchmarks and real-world images.