What it does
Identifies regions of interests on package labels such as sender's name, sender's address, recipient's name, recipient's address, contents description, total weight, and total value.
How we built it
This project uses OpenCV to preprocessed the images (removing background, rotation) and uses the machine learning algorithm YOLO to identify regions of interest on test images.
Challenges we ran into
- Lack of sleep
- Preprocessing labeled bounding boxes on training sets to match preprocessed training images
Accomplishments that we're proud of
- ## What we learned
Log in or sign up for Devpost to join the conversation.