TabAug: Data Driven Augmentation for Enhanced Table Structure Recognition
This addresses the problem of limited and expensive labeled data for table structure recognition in document images, offering a domain-specific solution that is incremental over standard augmentation techniques.
The paper tackles the lack of effective data augmentation for table structure recognition by proposing TabAug, a data-driven method that replicates and deletes rows and columns, improving cell-level detection accuracy from 92.16% to 96.11% on the ICDAR 2013 dataset.
Table Structure Recognition is an essential part of end-to-end tabular data extraction in document images. The recent success of deep learning model architectures in computer vision remains to be non-reflective in table structure recognition, largely because extensive datasets for this domain are still unavailable while labeling new data is expensive and time-consuming. Traditionally, in computer vision, these challenges are addressed by standard augmentation techniques that are based on image transformations like color jittering and random cropping. As demonstrated by our experiments, these techniques are not effective for the task of table structure recognition. In this paper, we propose TabAug, a re-imagined Data Augmentation technique that produces structural changes in table images through replication and deletion of rows and columns. It also consists of a data-driven probabilistic model that allows control over the augmentation process. To demonstrate the efficacy of our approach, we perform experimentation on ICDAR 2013 dataset where our approach shows consistent improvements in all aspects of the evaluation metrics, with cell-level correct detections improving from 92.16% to 96.11% over the baseline.