Offline handwritten mathematical expression recognition with graph encoder and transformer decoder
文献类型：期刊论文
| 作者 | Tang, Jia-Man1,2; Guo, Hong-Yu2,3; Wu, Jin-Wen2,3 ; Yin, Fei2,3; Huang, Lin-Lin1
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 148页码:11 |
| ISSN号 | 0031-3203 |
| 关键词 | Handwritten mathematical expression recognition Symbol detection Graph Neural Network Transformer |
| DOI | 10.1016/j.patcog.2023.110155 |
| 通讯作者 | Huang, Lin-Lin(huangll@bjtu.edu.cn) |
| 英文摘要 | Handwritten mathematical expression recognition (H MER) has attracted extensive attention. Despite the significant progress achieved in recent years attributed to the development of deep learning approaches, HMER remains a challenge due to the complex spatial structure and variable writing styles. Encoder-decoder models with attention mechanism, which treats HMER as an image-to-sequence (i.e. LaTeX) generation task, have boosted the accuracy, but suffer from low interpretability in that the symbols are not segmented explicitly. Symbol segmentation is desired for facilitating post-processing and human interaction in real applications. In this paper, we formulate the mathematical expression as a graph and propose a Graph-Encoder-Transformer-Decoder (GETD) approach for HMER . For constructing the graph from input image, candidate symbols are first detected using an object detector and represented as the nodes of a graph, called symbol graph, and the edges of the graph encodes the between-symbol relationship. The spatial information is aggregated in a graph neural network (GNN), and a Transformer-based decoder is used to identify the symbol classes and structure from the graph. Experiments on public datasets demonstrate that our GETD model achieves competitive expression recognition performance while offering good interpretability compared with previous methods. |
| 资助项目 | National Key Research and Development Program, China[2020AAA0109702] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | ELSEVIER SCI LTD |
| WOS记录号 | WOS:001128098400001 |
| 资助机构 | National Key Research and Development Program, China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/54877]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Huang, Lin-Lin |
| 作者单位 | 1.Beijing Jiaotong Univ, Sch Elect & Informat Engn, Beijing 100044, Peoples R China 2.Chinese Acad Sci, State Key Lab Multimodal Artificial Intelligence S, Inst Automat, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tang, Jia-Man,Guo, Hong-Yu,Wu, Jin-Wen,et al. Offline handwritten mathematical expression recognition with graph encoder and transformer decoder[J]. PATTERN RECOGNITION,2024,148:11. |
| APA | Tang, Jia-Man,Guo, Hong-Yu,Wu, Jin-Wen,Yin, Fei,&Huang, Lin-Lin.(2024).Offline handwritten mathematical expression recognition with graph encoder and transformer decoder.PATTERN RECOGNITION,148,11. |
| MLA | Tang, Jia-Man,et al."Offline handwritten mathematical expression recognition with graph encoder and transformer decoder".PATTERN RECOGNITION 148(2024):11. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。