Intelligently Extract Text & Data from Document with OCR NER

Develop Document Scanner App project that is Named entity extraction from scan documents with OpenCV, Pytesseract, Spacy

4.53 (324 reviews)
Udemy
platform
English
language
Data Science
category
instructor
Intelligently Extract Text & Data from Document with OCR NER
2,967
students
7.5 hours
content
Nov 2023
last update
$69.99
regular price

What you will learn

Develop and Train Named Entity Recognition Model

Not only Extract text from the Image but also Extract Entities from Business Card

Develop Business Card Scanner like ABBY from Scratch

High Level Data Preprocess Techniques for Natural Language Problem

Real Time NER apps

Why take this course?

Welcome to Course "Intelligently Extract Text & Data from Document with OCR NER" !!!

In this course you will learn how to develop customized Named Entity Recognizer. The main idea of this course is to extract entities from the scanned documents like invoice, Business Card, Shipping Bill, Bill of Lading documents etc. However, for the sake of data privacy we restricted our views to Business Card. But you can use the framework explained to all kinds of financial documents. Below given is the curriculum we are following to develop the project.

To develop this project we will use two main technologies in data science are,

  1. Computer Vision

  2. Natural Language Processing

In Computer Vision module, we will scan the document, identify the location of text and finally extract text from the image. Then in Natural language processing, we will extract the entitles from the text and do necessary text cleaning and parse the entities form the text.


Python Libraries used in Computer Vision Module.

  • OpenCV

  • Numpy

  • Pytesseract

Python Libraries used in Natural Language Processing

  • Spacy

  • Pandas

  • Regular Expression

  • String


As are combining two major technologies to develop the project, for the sake of easy to understand we divide the course into several stage of development.

Stage -1: We will setup the project by doing the necessary installations and requirements.

  • Install Python

  • Install Dependencies

Stage -2: We will do data preparation. That is we will extract text from images using Pytesseract and also do necessary cleaning.

  • Gather Images

  • Overview on Pytesseract

  • Extract Text from all Image

  • Clean and Prepare text

Stage -3: We will see how to label NER data using BIO tagging.

  • Manually Labeling with BIO technique

    • B - Beginning

    • I  -  Inside

    • O - Outside

Stage -4: We will further clean the text and preprocess the data for to train machine learning.

  • Prepare Training Data for Spacy

  • Convert data into spacy format

Stage -5: With the preprocess data we will train the Named Entity model.

  • Configuring NER Model

  • Train the model

Stage -6: We will predict the entitles using NER and model and create data pipeline for parsing text.

  • Load Model

  • Render and Serve with Displacy

  • Draw Bounding Box on Image

  • Parse Entitles from Text


Finally, we will put all together and create document scanner app.

Are you ready !!!

Let start developing the Artificial Intelligence project.

Reviews

Banyay
March 10, 2023
About labeling. I think it should take less then 8 hours. We could use Excel VBA or Python code with regular expressions for labeling. Else is all good.
Antonio
February 7, 2023
Hello, I am struggling with this same issue which a number of others seemed to hit, i.e. the installation of Tesseract and Pytesseract. Your course video only show for Windows, bit disappointing that you chose not to explain MacOs installation of Tesseract in same detail. On MacOs it is not so straightforward. What is the point if you do not give a step for step? This is a paid training course, not a Youtube video. Could you assist me?
Björn
December 5, 2022
Overall it is a good course with an adequate speed. However, sometimes the presented code is not really explained in sufficient detail for intermediate developers to fully understand it. In addition, I would have liked to see an evaluation of alternative options to Pytesseract to improve the results of the OCR process.
R
November 11, 2022
Lots of good information. The webapp section can be improved with more detailed explanation. Not everyone is familiar with Ajax, JS and DJango.
Imran
September 10, 2022
This is total misleading, This is not something intelligently extracting data. There is too much manual tagging work for each card. If we have to do manual tagging for each card then it would be better to manually extract all information, useless course. I am apply refund
Florian
August 15, 2022
Well explained and precicely on the point. Really understood the necessary steps very easily. Would have appreciated some PDF samples containing tabular. But this would have just been a bonus.
Armin
July 31, 2022
With my three stars I am not evaluating the course itself but my experience with the learning contents. The missing stars are missing due to the fact that I was unable to load the spacy config file. I tried for days installing and reinstalling spacy and searching for a solution in the web. So two thirds of the course were irrelevant for me (although I followed part of the following lectures as as an observer). I am working on a Mac and I used Anaconda distribution. The few hints in the course for Mac were not sufficient for me. It is not the fault of the author, if I was unable to install the environment correctly, but at least, the course should offer what other courses offer: some alternatives and more focus on critical aspects. Installing Tesseract/Pytesseract, CV and Spacy is not trivial and you can find plenty of users with problems in the web. By the way: did the author know that closing images on Mac requires a restart of the kernel (at least to what I discovered and to what the Portilla course (CV) is teaching)? Concerning the proposed topic and solution, I find the course an overkill. Maybe there are no other coding solutions available than all these infinite steps (and that of manual labeling all this information) but I bet, that I am faster doing the process manually faster than a non-expert can do it with the proposed coding. To close my comments in a positive way, I got the impression, that the author is a real expert and the course gave me quite some new coding tips. Thanks for that.
Omid
December 30, 2021
This course is fantastic, i had a same project and helped me a lot to train my own NER model for intelligently extracting data from invoices.
Alan
November 29, 2021
I find this course festinating and the instructor teaches by example which I prefer and questions are dealt with quickly. The section on solving problems you might have with the code is a very good idea.

Charts

Price

Intelligently Extract Text & Data from Document with OCR NER - Price chart

Rating

Intelligently Extract Text & Data from Document with OCR NER - Ratings chart

Enrollment distribution

Intelligently Extract Text & Data from Document with OCR NER - Distribution chart

Related Topics

4107158
udemy ID
6/7/2021
course created date
11/11/2021
course indexed date
Bot
course submited by