Application of Image Recognition and Machine Learning Technologies for Payment Data Processing Review and Challenges

2017 5th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE 2017): Proceedings 2017
Artjoms Supoņenkovs, Jānis Grabis, Jānis Kampars, Aleksandrs Sisojevs, Krišjānis Pinka, Guntis Mosāns, Romāns Taranovs, Audris Locmelis

The automatic receipt analysis problem is very relevant due to high cost of manual document processing. Therefore, the presented paper investigates the problems of receipt image analysis. It describes approaches for receipt image pre-processing, receipt text detection, receipt text recognition and receipt text analysis. These approaches allow to make receipt analysis system adaptable for a real-life environment and to convert the input information to a usable format for analysing information in the receipts. A pipeline for payment data processing staring with image capture to payment data posting is defined and appropriate technologies for every stage of the process are proposed. Advantages and limitations of these technologies are reviewed and open research challenges are identified. The payment data processing is analyzed as an enabler of digital transformation of expense reporting processes.

Atslēgas vārdi
Image recognition, machine learning technologies, data processing
DOI
10.1109/AIEEE.2017.8270536
Hipersaite
http://ieeexplore.ieee.org/document/8270536/

Supoņenkovs, A., Grabis, J., Kampars, J., Sisojevs, A., Pinka, K., Mosāns, G., Taranovs, R., Locmelis, A. Application of Image Recognition and Machine Learning Technologies for Payment Data Processing Review and Challenges. No: 2017 5th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE 2017): Proceedings, Latvija, Rīga, 24.-25. novembris, 2017. Piscataway: IEEE, 2017, 1.-6.lpp. ISBN 978-1-5386-4138-5. e-ISBN 978-1-5386-4137-8. Pieejams: doi:10.1109/AIEEE.2017.8270536

Publikācijas valoda
English (en)