Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Sign Language Recognition

No description
by

NeRvana IsMail

on 15 June 2014

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Sign Language Recognition

Biomedical Engineering Department
Sign Language
Flow Chart
Sign Language Recognition
using Neural Network

Types Of NN:
Introduction
Project Idea :
Converting sign language to text or speech.

Our Target :
Ease the communication between deaf and general communities.

Under Supervision of :
Dr. Amal El-Desouky

List of sign languages:

- Signed modes "Manually Coded Languages",




- Auxiliary sign systems.
2013 / 2014
Examples from sign languages :
British Sign Language
American Sign Language
Arabic Sign Language
Neural Network
Simple Recurrent Networks
Self Organizing Maps
3D Hopfield

Back Propagation
Main Idea
Presented by

Video Capture
Face Detection
GUI Explanation
& Matlab Codes

. Beshoy Adel
. Diana Ismail
. Michael Guirguis

Agenda
Introduction
Sign Language
Neural Network
GUI Explanation
Matlab Code
Conclusion
Future Work
Title
GUI
Explanation
(1) Video Recording
(2) Face Detection
(3) Hand Segmentation
(4) Motion Detection
(5) NN Training
(6) NN Testing
Difficulties that led to the problem
Restaurants
& Cafes
Government departments
Education
Using Phones
Driving
Wake up in the morning
Deal with emergencies
Watch television or movies
Connect with the society
Project
Health Care
>> obj = videoinput
(adaptorname);
>> [output,count,m
,svec]=facefind(x,
minf,maxf,dx,dy
,sens);
>> plotbox
(output,col,t);
Hand Segmentation
>> C =
makecform(type);
Hand Trajectory
Neural Network Training
Neural Network Testing
>> net = newff(inputs,target,10);
>> load net
>>result=sim(net
,feature_vector');
>>y2=find
(result==max
(result));
>> net = train
(net,inputs,
target);
or
of the recorded video
Number of Frames
The primary features
of the face
the eyes,
nose,
mouth
and ears .
* 1st order statistical Grey-Level features
mean
standard deviation
skewness
kurtosis
entropy
* Distance
Lab
R
G
B
bw Lable
Closing
Center of object
Input Matrix
= 12*120
Target = 8*120
=>
Lab
The Max Weight refers to the desired word
W
w
w
w
w
max
1
w
2
3
n
4
Finally, from the data base the word with the highest wight selected to be the represented sign.
Conclusion
more than
%
doesn't exceed
.
mins
Words
&
Sentence
Future Work
Discussion
The End
Full transcript