Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using ChatGPT as a Combined Invoice OCR and Key-Value Extractor
Linnaeus University.
Linnaeus University.
Fortnox, Växjö, Sweden.
Linnaeus University.
Show others and affiliations
2025 (English)In: 2025 10th International Conference on Big Data Analytics, ICBDA 2025, Institute of Electrical and Electronics Engineers (IEEE), 2025, p. 320-325Conference paper, Published paper (Refereed)
Abstract [en]

This paper provides details and analysis of findings from three experiments on the capabilities of the OpenAI chatbot ChatGPT-4 with vision capabilities as a dual-purpose tool for Optical Character Recognition (OCR) and key-value data extraction tasks. Our results could be relevant to any task where one is interested in extracting key information from images with approximately equal complexity, and are scalable to be used for large datasets. We did the main experiments in the OpenAI user interface for the model, and a smaller experiment using the API. The experiment used a dataset comprising 1000 digital invoices alongside 1000 photographic images of real receipts, collected from a broad spectrum of market sectors within Sweden. The main experiment gave us a significant accuracy rate, achieving $\mathbf{9 9. 8 \%}$ in extracting critical financial information from the digital invoices. Similarly, when applied to the photographic images of receipts, it maintained a high accuracy level of $\mathbf{9 9. 5 \%}$. The smaller experiment gave us an accuracy of $\mathbf{9 4. 4 \%}$ These findings are particularly noteworthy not only because of the high accuracy levels but also due to the model's effectiveness in performing both OCR and key-value extraction tasks as a one-step process. This dual functionality underscores the model's potential as a highly efficient and reliable solution in automating financial data extraction and processing tasks. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2025. p. 320-325
Keywords [en]
Key-Value Extraction, Large Language Model, Optical Character Recognition, Application programming interfaces (API), Data accuracy, Data handling, Data mining, Extraction, Financial data processing, Large datasets, User interfaces, Accuracy level, Chatbots, Data extraction, High-accuracy, Key values, Language model, Optical-, Photographic image, Photography
National Category
Artificial Intelligence Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:bth-28995DOI: 10.1109/ICBDA65366.2025.11211156ISI: 001860316100046Scopus ID: 2-s2.0-105023839703ISBN: 9798331503932 (print)OAI: oai:DiVA.org:bth-28995DiVA, id: diva2:2020966
Conference
10th International Conference on Big Data Analytics, ICBDA 2025, Singapore, March 13-15, 2025
Available from: 2025-12-12 Created: 2025-12-12 Last updated: 2026-09-18Bibliographically approved

Open Access in DiVA

fulltext(305 kB)156 downloads
File information
File name FULLTEXT01.pdfFile size 305 kBChecksum SHA-512
5c23c0f553acd1bf5e6e944113e6793d69ea126803a6a79cbc2424c51d9291b6e17a93baba0decd240a31262cd2c7567e5eacd6245f8fee8334c181e4d17d0f6
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Grahn, Håkan

Search in DiVA

By author/editor
Grahn, Håkan
By organisation
Department of Computer Science
Artificial IntelligenceComputer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar
Total: 158 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 1100 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf