Deep Structured Feature Networks for Table Detection and Tabular Data Extraction from Scanned Financial Document Images

TL;DR

This paper introduces a deep learning-based method for detecting tables and extracting tabular data from scanned financial PDFs, addressing challenges like noise and data integrity for improved financial data processing.

Contribution

It presents a new annotated dataset for financial documents, a superior detection model using Faster R-CNN with FPN, and a rule-based layout segmentation technique for accurate data extraction.

Findings

High table detection accuracy on the new dataset

Effective extraction of structured tabular data

Scalable rule-based filtering improves data quality

Abstract

Automatic table detection in PDF documents has achieved a great success but tabular data extraction are still challenging due to the integrity and noise issues in detected table areas. The accurate data extraction is extremely crucial in finance area. Inspired by this, the aim of this research is proposing an automated table detection and tabular data extraction from financial PDF documents. We proposed a method that consists of three main processes, which are detecting table areas with a Faster R-CNN (Region-based Convolutional Neural Network) model with Feature Pyramid Network (FPN) on each page image, extracting contents and structures by a compounded layout segmentation technique based on optical character recognition (OCR) and formulating regular expression rules for table header separation. The tabular data extraction feature is embedded with rule-based filtering and restructuring functions that are highly scalable. We annotate a new Financial Documents dataset with table regions for the experiment. The excellent table detection performance of the detection model is obtained from our customized dataset. The main contributions of this paper are proposing the Financial Documents dataset with table-area annotations, the superior detection model and the rule-based layout segmentation technique for the tabular data extraction from PDF files.