Continue to Site

Welcome to our site!

Electro Tech is an online community (with over 170,000 members) who enjoy talking about and building electronic circuits, projects and gadgets. To participate you need to register. Registration is free. Click here to register now.

  • Welcome to our site! Electro Tech is an online community (with over 170,000 members) who enjoy talking about and building electronic circuits, projects and gadgets. To participate you need to register. Registration is free. Click here to register now.

Sign Language Translator

Status
Not open for further replies.

KaRyu

New Member
I would like to ask some help here.

This is my project.
I still don't know how to implement this.
I need an opinion on what device should I use.
Should I use a webcam?
-I considered this but with a computer the device will not be portable.
Should I use a cellphone?
-This makes it portable. But I don't know if the memory of a cellphone is enough to do complicated programs.
should I create a new device specifically for that?
-I don't have any idea on how to make a separate device.

Thanks.
 
These devices already exist where the deaf person signs and the device produces a verbal translation. Search google for something similar.

>> Should I use a webcam?
>> -I considered this but with a computer the device will not be portable.
If portability is one of your requirements, then don't use a non-portable computer.

>> Should I use a cellphone?
>> -This makes it portable. But I don't know if the memory of a cellphone is enough to do complicated programs.
AFAIK, for an Android device, you should be able to access a fair bit of the device's memory if you use C/C++ and compile to native code. Otherwise the Java runtime will limit you to 16/24/48MB (depending on your OS version). Smart phones are pretty impressive performers... just make sure your algorithm is lean.

>> should I create a new device specifically for that?
>> -I don't have any idea on how to make a separate device.
If this is a project that you must do, then this is not a suitable starting point.

I suggest that you develop the algorithm on a PC using a high level language, e.g. Matlab is very good for quick algorithm development, processing a recorded video (to give something consistent to test against) rather than interfacing the webcam. Once you have the algorithm working, you can port it to a mobile phone.
 
If I create an algorithm on matlab, how can i transfer it into a mobile phone?
Once it's working, you rewrite it in whatever language is required for the mobile device. e.g. C++ or Java for Android and Objective C for iOS
 
what is the most efficient method for hand sign recognition? we are thinking of using glove or color mark
Yeah, a coloured glove of the right colour will make the segmentation very easy and effective. If you use multiple colours you could make it simpler to work out exactly which blob is which finger, which side (front/back), etc.
 
Our project doesn't only lies with translating sign language into words, but also words into SL
any suggestion on how to do that?
 
Status
Not open for further replies.

Latest threads

New Articles From Microcontroller Tips

Back
Top