OCRGemini Invoice Processor
An invoice processing system that automates extraction of invoice information from PDF files using Google's Gemini AI model. Handles both single and multi-invoice PDFs, converts pages to images, resizes for consistency, concatenates vertically, and outputs structured CSV data.
Project Duration
Nov 2024 — Nov 2024
Client
Finance ClientNDA
Key Features
PDF to image conversion
Multi-invoice handling
Gemini AI extraction
CSV output
Image preprocessing
Batch processing
Technology Stack
PythonGoogle Geminipdf2imageOpenCVPandasPillow
Project Metrics
98%
accuracy
5000+
invoices
< 10s
speed
Interested in a Similar Project?
Let's discuss how we can build something amazing for your business.
