A Two-stage Approach for Tables Extraction in Invoices

Abstract

The automated analysis of administrative documents is an important field in document recognition that is studied for decades. Invoices are key documents among the documents available in companies and public services. Most of the time, invoices include data that are presented in tables. These tables must be clearly identified to extract suitable information. In this paper, we propose an approach that combines an image processing-based estimation of the shape of the tables with a graph-based representation of the document. We aim to precisely identify different types of tables, including possible complex layouts. We propose an experimental evaluation using a real case application and a classic dataset.