Plane Geometry Diagram Parsing
This work addresses the problem of automating geometry problem solving for educational or AI applications, but it is incremental as it builds on existing methods with modifications and new data.
The paper tackles geometry diagram parsing by proposing PGDPNet, an end-to-end deep learning model that integrates instance segmentation and graph neural networks to extract primitives and parse relations, achieving state-of-the-art performance on new and existing datasets with remarkable improvements in four sub-tasks.
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.