Towards Analysing Invoices and Receipts with Amazon Textract
Abstract
This paper presents an evaluation of the AWS Textract in the context of extracting data from receipts. We analyse Textract functionalities using a dataset that includes receipts of varied formats and conditions. Our analysis provided a qualitative view of Textract strengths and limitations. While the receipts totals were consistently detected, we also observed typical issues and irregularities that were often influenced by image quality and layout. Based on the analysis of the observations, we propose mitigation strategies.
Links & Resources
Authors
Cite This Paper
Oommen, S., Sanchez, G., Britto, C. T., Wang, D., Chiou, J., Spichkova, M. (2025). Towards Analysing Invoices and Receipts with Amazon Textract. arXiv preprint arXiv:2512.19958.
Sneha Oommen, Gabby Sanchez, Cassandra T. Britto, Di Wang, Jordan Chiou, and Maria Spichkova. "Towards Analysing Invoices and Receipts with Amazon Textract." arXiv preprint arXiv:2512.19958 (2025).