On Cropped versus Uncropped Training Sets in Tabular Structure Detection
This addresses dataset preparation for automated document processing in organizations, but it is incremental as it focuses on a specific aspect of existing methods.
The study compared table structure detection performance using cropped versus uncropped datasets, finding that deep learning models improved detection by up to 9% in average precision and recall on cropped versions, with significant gains beyond 70% IoU thresholds.
Automated document processing for tabular information extraction is highly desired in many organizations, from industry to government. Prior works have addressed this problem under table detection and table structure detection tasks. Proposed solutions leveraging deep learning approaches have been giving promising results in these tasks. However, the impact of dataset structures on table structure detection has not been investigated. In this study, we provide a comparison of table structure detection performance with cropped and uncropped datasets. The cropped set consists of only table images that are cropped from documents assuming tables are detected perfectly. The uncropped set consists of regular document images. Experiments show that deep learning models can improve the detection performance by up to 9% in average precision and average recall on the cropped versions. Furthermore, the impact of cropped images is negligible under the Intersection over Union (IoU) values of 50%-70% when compared to the uncropped versions. However, beyond 70% IoU thresholds, cropped datasets provide significantly higher detection performance.