[Student-projects] Re : [ Project Idea on Sign Recognition]

[Reetesh Ranjan]

Hi Santosh Sir,
 Yes Sir, you are correct about the project idea.
It includes the video  processing and then using those processed data to
train our model.
Sign language is a visual language and consists of 3 major components:

   - finger-spelling: used to spell words letter by letter
   - word level sign vocabulary: used for the majority of communication
   - non-manual features: facial expressions and tongue, mouth and body
   position

To devise all the above three would be a difficult task in three months.
But, yes first two could be done in the given time of which the second one
is the most important. There are many proposed algorithms for the above
task, one of them is Markov
Models<http://research.gallaudet.edu/~cvogler/research/data/cvdm-iccv99.pdf>
 .
For this we will be required to work on OpenCV.


Kind Regards,
Reetesh Ranjan

Reetesh Ranjan
Junior Undergraduate
IIT(BHU), Varanasi
contact no: +917275115929
Skype : reetesh.ranjan11
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.smc.org.in/pipermail/student-projects-smc.org.in/attachments/20140228/767cc5b6/attachment-0001.htm>