Inspiration
Many times, biology research results from experiments end up taking a long time to be analyzed and are tedious. Automating this would speed up the process, allow scientists to have more time for other projects, and see results of their experiments faster.
What it does
This analyzes photos of multiple types of cells and identifies which cells are which. It keeps track of how many there are, labels the cells on a separate image allowing you to see where the program made its decisions.
How I built it
I used the OpenCV framework and Python.
Challenges I ran into
The images I was using to test the program were pretty saturated, so it was difficult to get rid of the background noise and achieve a high accuracy.
Accomplishments that I'm proud of
I've never used OpenCV before, and this is one of my first independent projects.
What I learned
How to use OpenCV, different types of feature detection.
What's next for Cell Identifier
Higher accuracy, more effective cell nuclei detection and background noise cancellation.
Log in or sign up for Devpost to join the conversation.