Document Scanner OPENCV PYTHON | Beginner Project

In this video, we are going to create a simple document scanner using OpenCV. We will learn how to run this in real-time and how we can save these images by pressing just a button on the keyboard. This Is a perfect project for beginners as it is simple and covers the core principles of OpenCV.

🚀🚀 My Urdu/Hindi AI YouTube Channel 🚀🚀

Code & Text Based Version:

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

[blahblahblah]

Thank you for this. You just made batch trading card photo editing and analysis 100x faster for me.

[MarkusBurrer]

To find the biggest contour you can simply use sort. You don't need to loop over the array yourself.

[khalidben]

you are doing a big favor to all of us new learners.Thank you so much for such great efforts

[komiagotsi]

Great tutorials, very clear, thanks! How can I detect automatically the best threshold1 and threashold2 ?

[scripachd]

How to fix errors in the code from the site:
lables[d] -> lables[d][c]

[nandandubey]

The video helped a lot!!! However when tried with different orientation of the document, it fails to warp the document.

[JoseHernandez-qkby]

Hi Murtaza

just to mention in minute 17:30 your code shows in line 81:
if cv2.waitKey(1) & 0xFF == ord('s'):

But downloadable file has:
if cv2.waitKey(1) & 0xFF == ord('s'):

[rulaneshedo]

very good Tutorial. thanks for sharing your knowledge with us

[Moprationsz]

Hey, amazing video! Please notice that the files in your course have some characters on their unicode form, crashing all the code.

[mohitangrish]

Can you please explain the working of reorder function

[myprojects-dfol]

Is the camera module or webcam you used for the video

[sangaweavers]

Grt vdo thanks for time saving but unable to get code as you refer description for code

[brownmax]

Hey... Can i apply it on handwritten images?

[sibghatullah]

Very nice work Mr. Murtaza, can you make a video on document layout analysis? To extract all tables in an image, i already wrote a code but due to inline space difference i can not use it for multiple layouts,

[mertcapkin]

For me it does not work.
I get an error: can't convert object of type list to str for text.
I did not change your code.

[B__PutriAuliaSN_DMekatronika]

can it be used to detect container images??

[DANIYALAMIR-qb]

Hi, can you provide the picture used in this example. Thanks!

[mksnkv]

thanks a lot for the video. I am trying to apply the program to a static image. I removed the infinite loop and just want a static plot of 6 images. The transformations went OK, but then I got such error:
SystemError: <built-in function putText> returned NULL without setting an error
while putting text on the plot of 6 images. Even if I comment the line, I got corrupted small black screen instead of image of 6 parts. Hope for response
P.S. I use OpenCV 4.2.0, Python 3.7 on Ubuntu OS

[xerogaming]

results are different for different cameras, code seems to work only for images with specific resolution, with any high resoltion like 4k, it cannot scan the image maybe due to extra noise

[JoseHernandez-qkby]

Hi Murtaza

I want to develope an cam scann to web application... for such target how the client's cam scamm connects to the web???