Inspiration
We wanted to do something with object detection and decided to have the computer detect coins would be a good start.
What it does
The user inputs an image and the computer detects how many coins are in the image.
How we built it
For our object detection, we first grayscale the image, then gaussian blurred it for smoother processing, then we used canny edge to figure out the outlines of the object, we dilate it to put emphasis on the edges, then our algorithm color coded the edges and read how many coins were present based on that.
Challenges we ran into
We ran into some front-end issues because we had no experience in developing the front end. Our front end had a lot of issues. Limited project experience led to poor time management.
Accomplishments that we're proud of
We were able to get a result out of our backend program which was a great accomplishment after failing to get the front end up and running.
What we learned
We learned how to process data, We honed our python and HTML skills. We also got a little bit of experience in front-end development.
What's next for Coin Counter using Object detection
We would be able to implement the front end successfully. We would then move on to videos or gifs of object detection not limited to coins.
Log in or sign up for Devpost to join the conversation.