Evaluating Table Structure Recognition: A New Perspective
Existing metrics used to evaluate table structure recognition algorithms have shortcomings with regard to capturing text and empty cells alignment. In this paper, we build on prior work and propose a new metric - TEDS based IOU similarity (TEDS (IOU)) for table structure recognition which uses bound...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Existing metrics used to evaluate table structure recognition algorithms have
shortcomings with regard to capturing text and empty cells alignment. In this
paper, we build on prior work and propose a new metric - TEDS based IOU
similarity (TEDS (IOU)) for table structure recognition which uses bounding
boxes instead of text while simultaneously being robust against the above
disadvantages. We demonstrate the effectiveness of our metric against previous
metrics through various examples. |
---|---|
DOI: | 10.48550/arxiv.2208.00385 |