OCR OpenCV in FORMS and RECEIPTS | Text Detection p.1/2

In this tutorial, we will learn how to run OCR OpenCV. We will first look at how to properly align the image and then extract data from the region of interest. Apart from the text, we will also look at how to get information from the checkbox.

🚀🚀 My Urdu/Hindi AI YouTube Channel 🚀🚀

Code & Files:
coming soon...

Premium Courses:
✔️ Computer Vision Game Development Course:
✔️ Computer Vision with Arduino Course:
✔️ Advanced Drone Programming Course:
✔️ Learn to Build Computer Vision Mobile Apps:
✔️ Jetson Nano Premium Course:

⚙️⚙️⚙️—-My Gear — ⚙️⚙️⚙️

Follow Me:

#ComputerVision
#OpenCV
#CVZone

[murtazasworkshop]

Code and Files now available for the OCR OpenCV on Forms and Receipts tutorial on the website.
(Under the Advance Section by the name "OCR on Forms and Receipts")

[AI_CANISTER]

I've studied a lot from you... Thank you sir....
Seeing your face for the first time....

[oxydol]

interesting topic. extracting data from random documents with high accuracy seems challenging.

[QuarktaschemitSenf]

excellent topic and tutorial! Liked and subbed!

[shirjeelkhan]

You are totally awesome. Great work go ahead. 👌

[RandyNasuta]

Hello sir, thanks for your explanation in this viewo. I want to ask, how to use trainned model (weight file) from YOLO to pytesseract? Thank you

[RafaelHarth]

First of all, thank you for your videos. I've made my own doc. scanner in C++ by following your tutorials.

Are you going to talk about line/form alignment? I'm interested on that... actually thats the issue I'm having now with my app.

Thank you again sir. Have a good one, see you soon.

[sibghatullah]

Good approach, but you are detecting image within image, you actually need to extract image using only single source image. May be by drawing contour on source image will help in this regard but you will need to rotate it according to text direction

[n.r.]

Sir you extract text, check box it is ok but image also there it means subimage, how to extract this subimage??? Please give me little bit idea

[aswinsampath]

Thank you so much!! It was great learning!

[sangeethask]

Sir I'm getting type error that Bfmatcher takes no argument how to resolve this ?

[Fogaca]

Could you tell me if the code could detect handwritten texts in form fields? Thank you for the tutorial.

[akshaykathiriya]

@Murtaza's Workshop - Robotics and AI merchandise Thank you sir for making this video, Sir the link given in description is dead. Can resend this link sir please!

[riyaz]

Please share the images and code.. the link which you provided in the comment session is not working..

[madhavimehta]

Hi, Thanks for your effort. I have checked ur website, there I didnt find the related material. Please share the exact link, it will be very helpful

[MrTalhakamran]

Murtaza, do we have library to read and write Urdu.
Thinking that if we are to increase effeciency at local level we would need that

[jasonrandy]

Thanks for the simple and clear steps. Unfortunately the link to the source code doesn't work. Can I have the new link please.

[srishtikumari]

Can I directlly convert from pdf (of multiple pages)?

[blackjackVIPs]

If I'm to make the system to detect handwriting instead of text, what should I use?

[rustemrustem]

Thank you very much for brilliant explanation. I came up with questions here. 1. How can I create API for this code? Should use Django+Rest API, or can I build API for machine learning models? 2. What is a ML model in your OCR code? I really appreciate if you could help me with that, thank you!