Click here to Skip to main content
13,409,239 members (41,733 online)
Rate this:
Please Sign up or sign in to vote.
Hi,i am an undergraduate student and our group hope to do a research on sign language Recognition area.In there we have a problem of breaking down a sentence into words which is shown by a deaf student.

ex: He goes to school

we want to track above sentence word by word.but the problem is they show the next sign soon after the current sign is finished.

Below link shows an example.[^]

Any Suggestions?
Posted 5-Jan-13 2:58am

1 solution

Rate this: bad
Please Sign up or sign in to vote.

Solution 1

Is there any specific spatial and temporal pattern for a single word?if the answer is yes, then just train your system on those smaller patterns which you have to identify manually during the training phase, but it also seems that sign language appears continuous, static recognition of gestures in sign language might not be a good choice, I suggest using a combination of spatial and temporal classification methods, probably using a kinetic sensor.

So have you started the implementation yet? That's an interesting project.

Hope this helps. :)
Hard_Rockz 10-Jan-13 12:25pm
Hi,thanks for your reply :-) are correct sign language appears continuously..that is the difficulty there...can you plz explain me how do i use the kinect sensor for spatial and temporal classification methods...because we are still doing background study for this research...we have to start our implementation by next month...Thank you again for your reply... :)
BupeChombaDerrick 10-Jan-13 15:04pm
You can use openCV to access kinetic RGB-D image,where D = depth, so I was assuming that using the depth map or channel can help in segmenting out the human from the background and then you can train neural networks on specific spatial and temporal signals from the segmented training examples. I have not done much of neural networks with temporal pattern recognition but maybe these two links below can help you with the kinetic sensor and openCv and spatial and temporal pattern recognition respectively.

Hard_Rockz 11-Jan-13 11:36am
Thank you very is so helpful :-)
BupeChombaDerrick 12-Jan-13 4:08am
You are welcome. :-)

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

  Print Answers RSS
Top Experts
Last 24hrsThis month

Advertise | Privacy |
Web02-2016 | 2.8.180212.1 | Last Updated 10 Jan 2013
Copyright © CodeProject, 1999-2018
All Rights Reserved. Terms of Service
Layout: fixed | fluid

CodeProject, 503-250 Ferrand Drive Toronto Ontario, M3C 3G8 Canada +1 416-849-8900 x 100