zzzDavid/ICDAR-2019-SROIE

ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

51
/ 100
Established

This project helps accounting, finance, and operations professionals automate data entry from scanned receipts. It takes scanned images of receipts as input and accurately extracts key information like company name, address, date, and total amount, outputting this data in a structured JSON format. This streamlines document processing and reduces manual effort for tasks such as expense reporting or transaction reconciliation.

411 stars. No commits in the last 6 months.

Use this if you need to automatically extract specific text fields from large volumes of scanned receipt images to populate databases or other financial systems.

Not ideal if you are working with complex, unstructured documents beyond simple receipts or require 100% perfect accuracy for every single field without any human review.

receipt-processing expense-management financial-operations document-automation data-entry-automation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

411

Forks

141

Language

Python

License

MIT

Last pushed

Jul 20, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/zzzDavid/ICDAR-2019-SROIE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.