# Extracting Tables from Documents using Conditional Generative Adversarial Networks and Genetic Algorithms

## TL;DR

This paper introduces a novel top-down method for extracting table structures from document images by combining generative adversarial networks and genetic algorithms to improve accuracy over traditional bottom-up approaches.

## Contribution

It proposes a new approach that first generates a skeleton of the table and then refines the structure using genetic algorithms, leveraging prior structural information.

## Key findings

- Effective extraction of table structures demonstrated
- Outperforms existing bottom-up methods
- Accurate mapping of table skeletons

## Abstract

Extracting information from tables in documents presents a significant challenge in many industries and in academic research. Existing methods which take a bottom-up approach of integrating lines into cells and rows or columns neglect the available prior information relating to table structure. Our proposed method takes a top-down approach, first using a generative adversarial network to map a table image into a standardised `skeleton' table form denoting the approximate row and column borders without table content, then fitting renderings of candidate latent table structures to the skeleton structure using a distance measure optimised by a genetic algorithm.