Generate Facial Filters with #Shaderbooth #Facemesh and #tensorflow.js #MachineLearning @maxbittker
@maxbittker recently released Shaderbooth.com which allows users to write and play with new indie face filters using GLSL. @maxbittker posted about the impetus for the project on twitter saying that he hopes that the website, “helps people to code fun effects that they can share with their friends” and encourages indie development of creative filters.
The code for each filter is superimposed on the screen so you can live edit. Once you’ve developed a filter you like, you can submit it to be part of the preset filters. This was my first time working with GLSL and I found it pretty straightforward. Below you can see some examples of changing the default “blue mask” to green and orange.
Shadderbooth.com uses tensorflow.js and the Facemesh machine learning pipeline to identify facial landmarks for the filters.
MediaPipe Facemesh is a lightweight machine learning pipeline predicting 486 3D facial landmarks to infer the approximate surface geometry of a human face.
If you’d like to learn more, the code for the project can be found on GitHub. If you’re curious about some of the effects built by other users, check out what I’m calling the ‘cyclops’ filter below. If you’d like to play with other similar projects that inspired Shaderbooth, check out hydra and shadertoy.
Written by Rebecca Minich, Product Analyst, Data Science at Google. Opinions expressed are solely my own and do not express the views or opinions of my employer.
Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.