Sign Alphabet Recognition

[KaRyu]

Can anyone suggest a good process( with algorithm) on this topic.

This topic uses webcam focused on the user's hand. the user spells the desired word. the webcam reads the sign alphabet.

Thanks in advance )

 

[Mr RB]

That's one of the hardest tasks you could ever do using a camera hooked to a computer.

I don't want to sound mean, but the way you have asked such a simple question probably indicates that you don't have the necessary high level of skill in image recognition and pattern decoding/AI algorithms that you would need to undertake this type of project.

 

[dougy83]

There are many ways to do this. Have a look at some existing methods, and it's probably easiest for you to use someone else's library or project as a starting point. e.g. http://sourceforge.net/projects/handgesturecs/
http://iris.usc.edu/people/thangdin/research.html
https://www.electro-tech-online.com/custompdfs/2013/06/starner1.pdf
http://www.google.com.au/search?q=sign+language+recognition&oq=sign+language+recognition

You can use the same methods used for partial facial recognition (e.g. SIFT, SRC), or if you could try processing the contours (probably less reliable).

 

[Jugurtha]

There's no way to do it with individual letters. The way people who can read lips do it is that the whole "word" fits a pattern and they look at the facial expression to check with their previous expression and what the other person. Just try to mute a movie: You'll probably guess when a person says "maybe" by the movement of their lips, and putting the things in their context. i.e: If it is in a formal conversation, it's more likely to be "maybe" than "baby".

All this adds complexity and one has to ask himself the question: Is it needed ? Especially when you know that it's easier to acquire sound than video.