Create an app where we input PDF pages of scanned documents and the system/script classifies the document images based on OCR text, then extracts data from certain zones on the page based on the type of document.
reference samples from google images for passports, bank checks and driver's licenses. Add invoices to the types of documents, so the system would have four possible known classifications: passport, Driver License, check, invoice. Anything not identified as one of those four is classified as "other".
As discussed, work must not rely on commercial packages or web services . Tesseract for OCR is fine.
17 freelanceů na tento projekt zveřejnilo nabídku v průměrné hodnotě $38/hod.
Hello sir I am a python developer with 7 years of professional experience. I am very experienced in tensorflow. I am interested in this job and can start the work right now. Best Zhang
Hello, How are you? I am very interested in your proposal. I have rich experience in this area. So I can satisfy you asap. Please let's have a contact and discuss further. Thanks & Regards!
Hello. My name is Xiao, and I am a Python developer you are looking for. I have been developing many Python scripts so far. And I am experienced in OCR with Python. So I can help you perfectly. Best regards.