Flexible Table Recognition and Semantic Interpretation System
This addresses the unsolved problem of table extraction for document analysis, but it is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of table extraction by introducing a flexible system with rule-based algorithms for table detection and segmentation, and a graph-based method for semantic interpretation, achieving an F1 score of 0.7380 on benchmarks like ICDAR 2013 and 2019.
Table extraction is an important but still unsolved problem. In this paper, we introduce a flexible and modular table extraction system. We develop two rule-based algorithms that perform the complete table recognition process, including table detection and segmentation, and support the most frequent table formats. Moreover, to incorporate the extraction of semantic information, we develop a graph-based table interpretation method. We conduct extensive experiments on the challenging table recognition benchmarks ICDAR 2013 and ICDAR 2019, achieving results competitive with state-of-the-art approaches. Our complete information extraction system exhibited a high F1 score of 0.7380. To support future research on information extraction from documents, we make the resources (ground-truth annotations, evaluation scripts, algorithm parameters) from our table interpretation experiment publicly available.