- Extract data from pdf
- Confert pdf to image (v)
- Get text from image using Tesseract-ocr (v)
- Determine if it is an invoice using ml
- Process the text with ml to see if it is an invoice
- Extract total amount, inv number and data
- Generate invoices of 10 different types
- Get 10 types of invoice templates of google
- Get fictive data to put on the invoice (company name, invoice ammount, etc)
- Generate 1k of each invoice
- Create ml model to sort invoices from non invoices
- Learn how to sort images using ML
- Sort images using ml