Invoice Data Extraction and Validation Pipeline Using OCR and Intelligent Rule-Based Verification

Authors

  • Aditya Sonawane Department of Computer Engineering, MVP Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, India
  • Sarvesh Mogal Department of Computer Engineering, MVP Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, India
  • Mayur Sahare Department of Computer Engineering, MVP Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, India
  • Vaishnavi Gughe Department of Computer Engineering, MVP Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, India
  • S. N. Khalane Department of Computer Engineering, MVP Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, India

DOI:

https://doi.org/10.69968/ijisem.2026v5i4331-342

Keywords:

Invoice Processing, OCR, Document Understanding, Information Extraction, Duplicate Detection, Accounts Payable

Abstract

Abstract This paper provides a comprehensive overview of the process for information retrieval from invoices. Invoices serve as proof of purchase and contain important information, including the date, description, quantity, and the price of goods or services, as well as the terms of payment. Invoice processing remains a document-intensive task in accounts payable (AP) because invoices arrive as heterogeneous PDFs, scans, photographs, and digitally generated files. Manual transcription and verification introduce delays and data-entry errors, while template-dependent systems struggle when vendor layouts change. This paper presents an invoice data extraction and validation pipeline that combines optical character recognition (OCR), pretrained document understanding, structured field extraction, deterministic validation, duplicate detection, persistent storage, and human review. The pipeline is event-driven and serverless: an invoice uploaded to a Cloud Storage bucket triggers a Cloud Function that calls the Google Cloud Document AI Invoice Parser, applies a configurable validation engine, and writes the result to separate clean and flagged BigQuery tables, with a Looker Studio dashboard and a Cloud Logging audit trail for monitoring. The contribution is not a new OCR model but an application-level architecture that treats extraction and validation as separate, connected stages. The validation layer checks required fields, arithmetic consistency, tax values, dates, vendor and value ranges, duplicate invoice identifiers, and confidence-based exceptions. A reproducible evaluation protocol is defined using field-level exact match, precision, recall, F1-score, validation pass rate, human-review rate, duplicate-detection accuracy, and processing time, with project targets of at least 95% field accuracy and 80% automated validation pass rate. Measured results are to be reported once the evaluation on a ground-truth dataset is complete.

References

[1] Y. Xu, M. Li, L. Cui, S. Huang, F. Wei, and M. Zhou, “LayoutLM: Pre-training of text and layout for document image understanding,” in Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2020, pp. 1192–1200.

[2] F. Krieger, P. Drews, and B. Funk, “Automated invoice processing: Machine learning-based information extraction for long tail suppliers,” Intell. Syst. Appl., vol. 20, Art. no. 200285, Nov. 2023, doi: 10.1016/j.iswa.2023.200285.

[3] C. Wang, J. Zhang, and Y. Yu, “Invoiveocr: Deep learning based automatic invoice recognition process,” Discover Artif. Intell., vol. 6, Art. no. 636, 2026, doi: 10.1007/s44163-026-01140-3.

[4] Google Cloud, “Uptrain a pretrained processor (Invoice Parser),” Document AI Documentation. Accessed: Oct. 29, 2026. [Online]. Available: https://cloud.google.com/document-ai/docs/uptrain-pretrained-processor

[5] Google Cloud, “Specialized processors with Document AI (Python),” Google Codelabs. Accessed: Oct. 29, 2026. [Online]. Available: https://codelabs.developers.google.com/codelabs/docai-specialized-processors

[6] T. Saout, F. Lardeux, and F. Saubion, “An overview of data extraction from invoices,” IEEE Access, vol. 12, pp. 19872–19886, 2024, doi: 10.1109/ACCESS.2024.3360528.

[7] H. T. Ha and A. Horák, “Information extraction from scanned invoice images using text analysis and layout features,” Signal Process., Image Commun., vol. 102, Art. no. 116601, Mar. 2022.

[8] Z. Yan, Z. Ye, J. Ge, J. Qin, J. Liu, Y. Cheng, and C. Gurrin, “DocExtractNet: A novel framework for enhanced information extraction from business documents,” Inf. Process. Manage., vol. 62, no. 3, Art. no. 104046, 2025, doi: 10.1016/j.ipm.2024.104046.

[9] T. Douzon, S. Duffner, C. Garcia, and J. Espinas, “Improving information extraction on business documents with specific pre-training tasks,” 2023, arXiv:2309.05429.

[10] R. R. Charabuddi, “Zero-shot invoice information extraction using foundation models with spatial prompt tuning,” Int. J. Intell. Syst. Appl. Eng., 2025. [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/7722

Downloads

Published

18-11-2026

Issue

Section

Articles

How to Cite

Aditya Sonawane, Sarvesh Mogal, Mayur Sahare, Vaishnavi Gughe, & S. N. Khalane. (2026). Invoice Data Extraction and Validation Pipeline Using OCR and Intelligent Rule-Based Verification. International Journal of Innovations in Science Engineering And Management, 5(4), 331-342. https://doi.org/10.69968/ijisem.2026v5i4331-342