DevMesh

Sign Recognizer

Udit Maherwal

Udit Maherwal

Jaipur, Rajasthan

0 0
  • 0 Collaborators

I created a sign recognizer using Tensorflow framework. I gained insights about how we can develop application which can help people in various aspects. ...learn more

Project status: Published/In Market

Artificial Intelligence

Code Samples [1]

Overview / Usage

Built an algorithm that would facilitate communications from a speech-impaired person to someone who doesn't understand sign language.

  • Training set: 1080 pictures (64 by 64 pixels) of signs representing numbers from 0 to 5 (180 pictures per number).
  • Test set: 120 pictures (64 by 64 pixels) of signs representing numbers from 0 to 5 (20 pictures per number).

Note that this is a subset of the SIGNS dataset. The complete dataset contains many more signs.

Methodology / Approach

I used SIGNS dataset and approach I used is basically not so complex. I took decent amount of data for training set and even more less for test. I had one hidden, you can implement more for futhermore accuracy or to get Bayesian Error level.

Technologies Used

I used tensorflow as my framework and python as my programming language.

Used libraries - numpy, matplotlib, math.

I developed this on jupyter notebook.

Repository

https://github.com/uditmaherwal/Signs-Recognizer

Comments (0)