In this project, you will learn to track faces in a video and identify facial expressions using Affectiva. As a fun visualization, you will tag each face with an appropriate emoji next to it. You will then turn this into a game where the player needs to mimic a random emoji displayed by the computer!
We’ll be using Affectiva’s Emotion-as-a-Service API for this project. Visit their Developer Portal and try out some of the sample apps. Affectiva makes it really easy to extract detailed information about faces in an image or video stream. To get a sense for what information you can obtain, check out the Metrics page.
To start working on the project, open the following files in your favorite text editor:
- mimic.js: Javascript file with code that connects to the Affectiva API and processes results.
- index.html: Dynamic webpage that displays the video feed and results.
- mimic.css: Stylesheet file that defines the layout and presentation for HTML elements.
There are two additional files provided for serving your project as a local web application - you do not need to make any changes to them:
- serve.py: A lightweight Python webserver required to serve the webpage over HTTPS, so that we can access the webcam feed.
- generate-pemfile.sh: A shell script you’ll need to run once to generate an SSL certificate for the webserver.
In order to access the webcam stream, modern browsers require you to serve your web app over HTTPS. To run locally, you will need to general an SSL certificate (this is a one-time step):
- Open a terminal or command-prompt, and ensure you are inside the
MimicMe/
directory. - Run the following shell script:
generate-pemfile.sh
This creates an SSL certificate file named my-ssl-cert.pem
that is used to serve over https.
Now you can launch the server using:
python serve.py
Note: The serve.py
script uses Python 3.
Alternately, you can put your HTML, JS and CSS files on an online platform (such as JSFiddle) and develop your project there.
Open a web browser and go to: https://localhost:4443/
- Hit the Start button to initiate face tracking. You may have to give permission for the app to access your webcam.
- Hit the Stop button to stop tracking and Reset to reset the detector (in case it becomes stuck or unstable).
- When you’re done, you can shutdown the server by pressing
Ctrl+C
at the terminal. Note: Your browser may notify you that your connection is not secure - that is because the SSL certificate you just created is not signed by an SSL Certificate Authority. This is okay, because we are using it only as a workaround to access the webcam. You can suppress the warning or choose "Proceed Anyway" to open the page.
As you work on your code, you may have to refer to resources in Affectiva's JS SDK documentation.