English

ClusterTabNet: Supervised clustering method for table detection and table structure recognition

Machine Learning 2024-05-24 v2 Computer Vision and Pattern Recognition

Abstract

We present a novel deep-learning-based method to cluster words in documents which we apply to detect and recognize tables given the OCR output. We interpret table structure bottom-up as a graph of relations between pairs of words (belonging to the same row, column, header, as well as to the same table) and use a transformer encoder model to predict its adjacency matrix. We demonstrate the performance of our method on the PubTables-1M dataset as well as PubTabNet and FinTabNet datasets. Compared to the current state-of-the-art detection methods such as DETR and Faster R-CNN, our method achieves similar or better accuracy, while requiring a significantly smaller model.

Keywords

Cite

@article{arxiv.2402.07502,
  title  = {ClusterTabNet: Supervised clustering method for table detection and table structure recognition},
  author = {Marek Polewczyk and Marco Spinaci},
  journal= {arXiv preprint arXiv:2402.07502},
  year   = {2024}
}

Comments

16 pages, 5 figures, accepted to ICDAR 2024. Code available at https://github.com/SAP-samples/clustertabnet

R2 v1 2026-06-28T14:45:46.615Z