AUTOMATING INVOICE PROCESSING THROUGH INTELLIGENT OPTICAL CHARACTER RECOGNITION AND ENTITY EXTRACTION

Hiroshi Martinez Camila

AUTOMATING INVOICE PROCESSING THROUGH INTELLIGENT OPTICAL CHARACTER RECOGNITION AND ENTITY EXTRACTION

Authors

Hiroshi Martinez Camila

Senior Machine Learning Engineer, Japan.

Keywords:

Automated Invoice Processing, OCR, Entity Extraction, Machine Learning, Document Understanding

Synopsis

Purpose: This paper investigates how intelligent Optical Character Recognition (OCR) combined with entity extraction techniques can automate invoice processing to improve accuracy and efficiency.

Design/methodology/approach: We propose a hybrid framework integrating OCR and structured data extraction using machine learning and natural language processing (NLP).

Findings: Results indicate that automated processing significantly reduces manual input, minimizes errors, and accelerates invoice handling.

Practical implications: The framework enables businesses to adopt scalable, touchless invoice processing workflows that reduce operational costs and improve financial data quality.

Originality/value: While existing systems focus on simple OCR, this work integrates entity extraction and context‑aware parsing optimized for real‑world invoice formats.

References

[1] Zhao, X., Wu, Z., Niu, E., & Wang, X. (2019). CUTIE: Learning to understand documents with Convolutional Universal Text Information Extractor. arXiv.

[2] Gummadi, V. P. K. (2019). Microservices architecture with APIs: Design, implementation, and MuleSoft integration. Journal of Electrical Systems, 15(4), 130–134. https://doi.org/10.52783/jes.9328

[3] Bardelli, C., Rondinelli, A., Vecchio, R., & Figini, S. (2020). Automatic electronic invoice classification using machine learning models. MDPI.

[4] Patel, S., & Bhatt, D. (2020). Abstractive information extraction from scanned invoices using end to end sequential approach. arXiv.

[5] Gummadi, V. P. K. (2020). API design and implementation: RAML and OpenAPI

[6] Guo, H., Qin, X., Liu, J., Han, J., & Ding, E. (2019). EATEN: Entity aware attention for sin

[7] Antonio, J. A., Putra, A. R., Abdurrohman, H. S. T. P., & Chandra, A. (2022). A survey on scanned receipts OCR and information extraction. ResearchGate.

[8] Ha, H. T. (2022). Information extraction from scanned invoice images using text analysis and layout features. (Related study).

[9] Automatic Electronic Invoice Classification Using Machine Learning Models. (2020). Journal Paper.

[10] Standard Accounts Payable Definition. Accounts payable. (n.d.). Wikipedia.

[11] Tesseract Optical Character Recognition Engine. Tesseract (software). (n.d.). Wikipedia.

[12] Gummadi, V. P. K. (2023). MuleSoft batch processing: High-volume streaming architecture. Computer Fraud & Security, 2023(12), 50–57. https://doi.org/10.52710/cfs.886

[13] Invoice OCR Practical Guide. OCR invoice processing: How it works & benefits. (2025).