naiveHobo/InvoiceNet
Deep neural network to extract intelligent information from invoice documents.
Implements an attend-copy-parse architecture based on RNNs for field-level extraction, with OCR preprocessing via Tesseract and configurable field types (general, amount, date, optional). Provides dual training and inference interfaces—a GUI trainer for custom dataset fine-tuning and an extractor supporting single/batch PDF processing—while enabling users to define custom invoice fields without modifying core code.
2,683 stars. No commits in the last 6 months.
Stars
2,683
Forks
415
Language
Python
License
MIT
Category
Last pushed
May 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/naiveHobo/InvoiceNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
paperless-ngx/paperless-ngx
A community-supported supercharged document management system: scan, index and archive all your documents
GoogleCloudPlatform/document-ai-samples
Sample applications and demos for Document AI, the end-to-end document processing platform on...
aphp/edspdf
EDS-PDF is a generic, pure-Python framework for text extraction from PDF documents. It provides...
aws-solutions/document-understanding-solution
Example of integrating & using Amazon Textract, Amazon Comprehend, Amazon Comprehend Medical,...
jonaswinkler/paperless-ng
A supercharged version of paperless: scan, index and archive all your physical documents