SEMv3: A Fast and Robust Approach to Table Separation Line Detection
This work addresses the challenge of detecting separation lines in wireless and deformed tables, which is crucial for accurate table parsing, but it appears incremental within the existing split-and-merge paradigm.
The paper tackles the problem of table separation line detection in table structure recognition, proposing SEMv3, which achieves state-of-the-art performance on public datasets like WTW, ICDAR-2019 cTDaR Historical, and iFLYTAB.
Table structure recognition (TSR) aims to parse the inherent structure of a table from its input image. The `"split-and-merge" paradigm is a pivotal approach to parse table structure, where the table separation line detection is crucial. However, challenges such as wireless and deformed tables make it demanding. In this paper, we adhere to the "split-and-merge" paradigm and propose SEMv3 (SEM: Split, Embed and Merge), a method that is both fast and robust for detecting table separation lines. During the split stage, we introduce a Keypoint Offset Regression (KOR) module, which effectively detects table separation lines by directly regressing the offset of each line relative to its keypoint proposals. Moreover, in the merge stage, we define a series of merge actions to efficiently describe the table structure based on table grids. Extensive ablation studies demonstrate that our proposed KOR module can detect table separation lines quickly and accurately. Furthermore, on public datasets (e.g. WTW, ICDAR-2019 cTDaR Historical and iFLYTAB), SEMv3 achieves state-of-the-art (SOTA) performance. The code is available at https://github.com/Chunchunwumu/SEMv3.