Table Detection in Document Images using Deep Learning

Abstract

Table detection is an essential step in many document analysis applications as tables are used for presenting structural and functional information to the reader. It is a hard problem due to varying table layouts. Researchers have proposed numerous techniques for table detection based on layout analysis of documents. Most of these techniques fail to generalize because they rely on hand engineered features which are not robust to layout variations. The project aims to develop a deep learning based method for table detection. In the proposed method, document images are first pre-processed. These images are then fed to a Region Proposal Network followed by a fully connected neural network for table detection. The proposed method works with high precision on document images with varying layouts that include documents, research papers, and magazines. It has also been evaluated on publicly available UNLV dataset where it beats Tesseract's state-of-the-art table detection system by a significant margin.