Design of Gestures to Text Applications

Communication is the exchange of thoughts, messages, or information, by speech, visual signals, writing, or behavior. Deaf and dumb people communicate among themselves using sign languages, but they find it difficult to expose themselves to the outside world. This project proposes a method for recog

Project Title

Design of Gestures to Text Applications

Project Area of Specialization

Biomedical Engineering

Project Summary

Communication is the exchange of thoughts, messages, or information, by speech, visual signals, writing, or behavior. Deaf and dumb people communicate among themselves using sign languages, but they find it difficult to expose themselves to the outside world. This project proposes a method for recognizing sign language characters given as input by the user in the form of hand gestures, using artificial intelligence in such a way that users can control home appliances by their gestures.

Project Objectives

Design a system that converts the gestures (performed as input signals by the user) to text for deaf and dumb people. 

Project Implementation Method

The term Electromyography refers to the measurement of the electrical parameters or activities due to the contraction of muscles and this information can be very useful in interpreting various neuromuscular activities.

We acquire the data using the Myo-Ware muscle sensor of Advancer Technologies keeping the fact that the human muscular system is electrical in nature and this fact can be used to build a new prototype that will be unconventional to other image-based systems.

The embedded system we are using to extract the signals is Arduino Mega because it is the most simplest and reliable one. 

An Offset circuit has been implemented because EMG signals possess negative values too and Arduino only gives us positive values. So, the offset circuit gives an offset to these values on the negative axis to the positive side.

Then further steps that have been implemented using MATLAB are

• Pre-Processing
• Segmentation
• Feature Extraction
• Classification

An accuracy of 80% has been achieved so far using the classifier Support Vector Machine (SVM).

Benefits of the Project

The sign language recognition has many applications including gesture-controlled activities like human-computer interaction, gesture-controlled home appliances, and other electronic devices, and many applications that use gesture as the trigger input.

Technical Details of Final Deliverable

This system will be unconventional from other image-based systems because we are using EMG signals as input by the user. Our future goal is to make a complete hardware prototype of this system that will be a real-time based designing and the text will be displayed on any visual device such as an LCD. 

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

Education , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Quality Education, Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com