TechHundred

• 

  We believe everyone deserves to be happy.

Inspiration

We at TechHundred people assistive technology can help them overcome their disability and make it easier for the disabled person to lead a normal life by integrating them more into society.

What it does

Translate ASL (American sign language) to text using a convolutional neural network.

For a blind person walking on the street, the software can help them navigate better by saying there is a human in-front or a potential danger.

How I built it

I used Keras to build the convolutional neural network, TensorFlow, Haar Cascade, Python, JavaScript and Flask

Challenges I ran into

Accomplishments that I'm proud of

Made the CNN from scratch without any API and had to do some serious reading on different websites. I was able to implement it alone given the time cranch.

What I learned

I learned a lot about machine learning and how we can use machine learning to make the life of a disabled person better.

What's next for TechHundred

I will try to train the neural network more so that I can improve the accuracy and I will also try to add more features to the software and perhaps a mobile application.

Built With

• cnn
• css
• flask
• html5
• javascript
• keras
• node.js
• numpy
• pandas
• python
• sk-learn
• tensorflow