Idea Details

Team and Contact Details

SNo Student Name School Degree Year Email
1Sarah IrfanSEECSUndergraduateFourth14besesirfan@seecs.edu.pk
1Laiqua AndleebSEECSUndergraduateFourth14beselandleeb@seecs.edu.pk
1Mehmoona BibiSEECSUndergraduateFourth14besembibi@seecs.edu.pk

Inter School Idea ? No
Do you need expertises from another area: No
If Yes please provide details of expertises you need:

Idea Details

Idea Name: SignPreter
Slogan: Lets communicate effectively
Supervisor Name: Imran Malik
Supervisor Designation: Assistant Professor
Supervisor School: SEECS
Supervisor Department: Separtment od Computing
Contact number: 03335225189
Email ID: malik.imran@seecs.edu.pk
Abstract:
    Communication gap between deaf/dumb and normal people is huge as people do not understand sign language.SignPreter is an easy communication source between deaf/dumb and people.
What is the unmet need in society that your idea will fulfill ?
    There is a huge communication gap between deaf and normal people. People who don’t know sign language are unable to interpret signs of deaf/dumb people and thus communication is affected. There is no such solution which converts sign language to text or speech and vice versa.
Who needs it ? How many would benefit ?
   Five percent population of world population is deaf and seventy million people use sign language as their mother language. A lot of people will benefit from this solution as it will help in effective communication between seventy million people who use sign language and normal people.
How will the solution works
    SignPreter is an android app which translates american sign language into text and speech. The person perform sign in front of camera, frames are extracted from the video and fed into deep learning algorithm convolution neural network. This CNN extracts features of the video and predict the sign. The CNN is trained on a training dataset comprising of gesture videos performed by multiple people with ten levels of lighting and shading
Who are your competitors ? How is your solution different
    There are apps like ProDeaf and Hand Talk Translator. We are trying to improve the features of application by using algorithms of CNN.
Status: new
Entry Date & Time: 2017-12-15 (2147)