[F4LT] Optical Character Recognition for Table Extraction from PDF

[mindpower]

Optical Character Recognition for Table Extraction from PDF
Building and deploying a PDF to Excel system using PaddleOCR and Fastapi
New
Rating: 3.0 out of 5
(1 rating)
257 students
1hr 6min of on-demand video

Description
Optical Character Recognition (OCR) systems are used in diverse industries today. With the development of better performing deep learning models, we are getting even better OCR solutions.

In this course, we shall take you on an amazing journey in which you'll implement and deploy a working OCR solution. To be more precise we shall build a working solution in which a user inputs a PDF file and gets all the tables contained in the PDF as excel sheets. We'll start from understanding how this system works, then build a working prototype on Google Colaboratory (Colab). From here, we shall build a simple API with the Fastapi framework. This will permit users input a PDF file and get as output a compressed file containing folders which themselves contain excel sheets with the different tables found in the PDF.

https://www.udemy.com/course/optical-character-recognition-for-table-extraction-from-pdf/

Enjoy!