Inspiration
Everyone has had the experience of a group photo being ruined by one blink. Our goal was to streamline the group photo process for both the average consumer and the professional photographer.
What it does
Instead of taking a single image at the end of a timer, our program takes a burst of 25 photos. Those photos are then fed through our computer vision software to pick the best photo of the 25, the best photo being the one with the most amount of people smiling with open eyes.
How we built it
We used python code our app and build the user interface, and to analyze the images for eyes and smiles we used the open source computer vision software OpenCV.
Challenges we ran into
OpenCV was invaluable in building our project, however OpenCV by default only shows you where the eyes and smile are, so one of our main challenges was creating a program that detects the number of open eyes and smiles in a picture. Another big challenge was building the Graphic User Interface with tkinter, our vision for Say Cheese is an easy to use application, we were very particular about what we wanted so we decided to code the entire GUI by hand instead of using Python GUI building software. This may have cost us time, but in the end it was the only way to ensure we got the end product we wanted.
Accomplishments that we're proud of
We successfully used OpenCV to detect open eyes and a smile from a webcam feed, which was simultaneously one of the most challenging and most important parts of the project. Additionally, we build a user interface from scratch with minimal experience beforehand.
What we learned
We learned an incredible amount over the course of our build. We learned how to implement OpenCV into a python script, how to build a GUI using Tkinter, and we learned how to utilize a built in webcam to take pictures and post a live video feed.
What's next for Say Cheese
We believe that our software has many uses in both the casual and professional side of photography. For the average consumer, our software can be built in to almost all modern smartphones, as most brands already use onboard facial recognition capabilities(Apple,Samsung,Google,Oneplus,LG,etc.). For the professional photographer, we could see this being built into camera software, which would be invaluable in situations such as weddings and other large social gatherings.
Log in or sign up for Devpost to join the conversation.