TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Mathematical Question Answering	Geometry3K	PGDPNet	Accuracy (%)	74.1	# 3
Scene Parsing	PGDP5K	PGDPNet	Total Accuracy	84.7	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/plane-geometry-diagram-parsing/scene-parsing-on-pgdp5k)](https://paperswithcode.com/sota/scene-parsing-on-pgdp5k?p=plane-geometry-diagram-parsing)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/plane-geometry-diagram-parsing/mathematical-question-answering-on-geometry3k)](https://paperswithcode.com/sota/mathematical-question-answering-on-geometry3k?p=plane-geometry-diagram-parsing)`

Plane Geometry Diagram Parsing

19 May 2022 · Ming-Liang Zhang, Fei Yin, Yi-Han Hao, Cheng-Lin Liu ·

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.

PDF Abstract