Blight-EYE

Link to the Hackathon submission

https://devpost.com/software/blight-eye

Inspiration

Recently large public datasets became available for training CNN models. We used a public dataset of skin disorders and Computer Vision to diagnose diseases using the camera feed. This tool enables preliminary diagnosis for a skin disorder to then be checked with a doctor.

What it does

Takes pictures of skin moles and uses a CNN utilizing fast feature extraction from the VGG network to return a possible diagnosis for a skin disorder.

Tech Specs

• GCP
• Android Native
• Android Material Design
• Volley (for handling requests)

Challenges we ran into

Figuring out why GCP returns so many [502s]. Giving our native Android application a usable feel. Sending byte arrays of images packed into JSON. (Did we even do this correctly? I guess what matters is that it worked. Though took some time for POSTS to arrive to the server because of the unreliable internet connection during our demo).