A System for the Automated Evaluation of Invoices

Abstract

This paper presents a system for the automated evaluation of invoices. The purpose of the system is to detect and recognize price entries of item tables in invoices. Due to the lack o f a l a yout model of all possible invoices the system is composed of several processing stages. These stages are: text stripe extraction and skew detection by a combination of mathematical morphology and heuristic search; orientation detection by a new approach called row-delta-histogram"; the optical character recognition of text stripes using a multilayer backpropagation network as a classi er and fractal based Peano features; table extraction which u s e s a genetic algorithm to adapt a suitable table row template; price entry extraction by using the context of optical character recognition. Also, the system comprises further functionalities, to name a few: reprocessing of all processing stages with di erent parameter settings, font t ypeface estimation and evaluation of divider information. The system runs as a C++ class library under the OS 2 operating system and shows encouraging recognition results.

A Two-stage Approach for Tables Extraction in Invoices

“…Ongoing research in this field focuses on addressing challenges related to invoice identification, information extraction, and table processing [1]. Initially, the task involved identifying invoices from document sets [3] leading to the development of models to facilitate their processing [4].…”

Machine Learning of Generalized Document Templates for Data Extraction

“…For example, Koppen et al (1998) describe a system for an automated evaluation of invoices. The purpose of the system is to detect and recognize price entries of item tables in invoices.…”

Genetic Algorithm Based Heuristic Measure for Pattern Similarity in Kirlian Photographs

“…A similar procedure for solving a pattern recognition problem was presented in [13]. There, in a system for automatic processing of invoices, the schematic similarity (but not equality) of invoice table rows was detected by running a genetic algorithm for a few generations, with the task of generating a bitstring pattern for all text rows of the document at once.…”