Built with a handy CV Web Scaffold (but the website almost completely written from scratch), this website holds a model which can detect fruit ripeness for apples (specifically ripe red apples vs green unripe apples), bananas, and blueberries. (Scaffold here: Github)
Made in 3 weeks from ground zero to ground hero 😆 @AICamp
Go to our website here.
Click on "Click to test fruit" and upload an image of a banana, apple, or blueberry. Our pretrained model will then detect the fruit and it's level of ripeness.
| Name | Role |
|---|---|
| Hyrum Hansen | Leader (instructor) |
| Andrew Wood | Product Manager & Web Developer (frontend and backend) |
| Reign OKeefe | Web Design & Web Developer (frontend) |
| Dhairya Viramgama | Data Scientist & Web Developer (frontend) |
| Aviel Wood | Data Scientist & Math/Statistician & Web Developer/Design (frontend) |
| Nabiha Jawad | Math/Sattistician & Web Developer (frontend and backend) |
| Rex Ouyang | Data Scientist & Web Developer (frontend) |
The roles mentioned above are the main ones each person did, however, everyone pretty much did a bit of every role.
Libraries
Technical Stack
-HTML, CSS, JS
API's / Tools
Data was obtained through a web scraping api (serp api + google)
Start by cloning this repo through the command line:
git clone https://github.com/Experance/Fripen-AI.git
After cloning this, clone ultralytics yolov5 in the app folder, by running
git clone https://github.com/ultralytics/yolov5.git
and
pip install -r yolov5/requirements.txt