Chasma - App for Blinds

• 

  App_Icon

Inspiration

Persons with blindness have difficulties identifying what is in front of them without touching or asking someone. This creates challenges, especially when there's no one to assist or if the object in front of them is not to be touched.

What it does

An Android Application which will let visually impaired users know the place and localize it within the given frame of the picture, we are using a pre-trained network for our object detection algorithm MSCOCO.

How we built it

We Used Android Studio for building the app and TensorFlow Lite for the mobile library for deploying models on mobile.

Challenges we ran into

I faced issues while integrating the machine learning trained model with the mobile device

Accomplishments that we're proud of

I was successfully able to build a working prototype app within the given time period

What we learned

How mobile apps and machine learning together can help the society

What's next for Chasma - App for Blinds

1). Enable voice input offline 2).Retrained and upgrade model with more objects i.e. electric wires, broken glass or dangerous objects 3).Navigation 4).Create a different modes of usage 5).Night vision

Built With

• ai
• android
• java
• machine-learning
• tensorflow
• tflite