Plane Geometry Diagram Parsing

TL;DR

This paper introduces PGDPNet, an end-to-end deep learning model that combines modified instance segmentation and graph neural networks to effectively parse geometry diagrams, improving primitive extraction and relation understanding.

Contribution

The paper presents a novel integrated model, PGDPNet, and a large-scale dataset PGDP5K for geometry diagram parsing, advancing the accuracy and efficiency of primitive and relation extraction.

Findings

Outperforms state-of-the-art methods on PGDP5K and IMP-Geometry3K datasets.

Achieves high accuracy in primitive extraction and relation parsing.

Demonstrates the effectiveness of combining deep learning with graph reasoning.

Abstract

Geometry diagram parsing plays a key role in geometry problem solving, wherein the primitive extraction and relation parsing remain challenging due to the complex layout and between-primitive relationship. In this paper, we propose a powerful diagram parser based on deep learning and graph reasoning. Specifically, a modified instance segmentation method is proposed to extract geometric primitives, and the graph neural network (GNN) is leveraged to realize relation parsing and primitive classification incorporating geometric features and prior knowledge. All the modules are integrated into an end-to-end model called PGDPNet to perform all the sub-tasks simultaneously. In addition, we build a new large-scale geometry diagram dataset named PGDP5K with primitive level annotations. Experiments on PGDP5K and an existing dataset IMP-Geometry3K show that our model outperforms state-of-the-art methods in four sub-tasks remarkably. Our code, dataset and appendix material are available at https://github.com/mingliangzhang2018/PGDP.