Knowledge Commons of Institute of Automation,CAS
Plane Geometry Diagram Parsing | |
Zhang Ming-Liang1,2![]() ![]() ![]() | |
2022-07 | |
会议名称 | Proceedings of the 31st International Joint Conference on Artificial Intelligence |
页码 | 1636-1643 |
会议日期 | 2022-7-24 |
会议地点 | 奥地利 维也纳 |
摘要 | 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. |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 文字识别与文档分析 |
国重实验室规划方向分类 | 认知决策知识体系 |
是否有论文关联数据集需要存交 | 是 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/55698 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhang Ming-Liang |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.School of Electronic Information Engineering, Beijing Jiaotong University |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang Ming-Liang,Yin Fei,Hao Yi-Han,et al. Plane Geometry Diagram Parsing[C],2022:1636-1643. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
0228.pdf(1024KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论