Git Product home page Git Product logo

Comments (10)

EvilPort2 avatar EvilPort2 commented on July 21, 2024

Can't help you without knowing the computer's software specifications and the exact error message. Sorry

from sign-language.

akash1725 avatar akash1725 commented on July 21, 2024

About recognize_gesture.py, this program worked. But when showing the hand signs, most of the time it is not showing any output whereas some other time it is showing "love" as the output.
My computer's specification is 4gb RAM, Intel core i5 with NVIDIA GEFORCE graphic card.

from sign-language.

EvilPort2 avatar EvilPort2 commented on July 21, 2024

It means that the recognition is not happening perfectly. Did you run the set_hand_hist.py file first before running fun_util.py or recognize_gesture.py?

from sign-language.

akash1725 avatar akash1725 commented on July 21, 2024

Yes, i did that. As far as I understood, that is for setting the image background and lighting conditions. Does the accuracy suffer in too bright or too dim lighting conditions?
And what should I keep in mind (like lighting conditions or distance between camera and hand) while running the code so that it gives output similar to the video you have uploaded

from sign-language.

EvilPort2 avatar EvilPort2 commented on July 21, 2024

In the video if you see the 'thresh' window, you will notice that it contains the outline of my hand and nothing else. In your case you should see your hands' outline, if you have set the hand histogram right. That is the perfect setting.

from sign-language.

akash1725 avatar akash1725 commented on July 21, 2024

i found that with changing the thresholding changes the output...like earlier it was detecting 'A' very well, now it doesnt. So just wanted to make sure whether the way i am doing thresholding is correct or not..in that 5*10 green box we have to place our hand so that the thresholded image has white region only where the hands are. What if it makes other region white as well if it has the skin color (like arms and face). Also is it fine if the box contains only the palm area (it fills it completely) or it should contain fingers as well??
I am assuming we have to place the palm area in the green box, not the other side of hand.
And if you have a video where you have shown how thresholding is done by you, it would be really helpful...

from sign-language.

EvilPort2 avatar EvilPort2 commented on July 21, 2024

Watch this video https://www.youtube.com/watch?v=KYfBLeYDMW4&feature=youtu.be

from sign-language.

cvyjojo avatar cvyjojo commented on July 21, 2024

still, give me wrong outport after setting up the histogram

from sign-language.

cvyjojo avatar cvyjojo commented on July 21, 2024

is it because you have merge other projects also with this model???

from sign-language.

EvilPort2 avatar EvilPort2 commented on July 21, 2024

Please download the latest repo. I have fixed those issues

from sign-language.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.