Using a Raspberry Pi 4 running OpenCV with a webcam for facial-recognition, the software (in Python) claims to calculate your innermost desirees, and then chooses the perfect lounge music song (played on three of my ArduTouch synthesizers, plus the open source eSpeak text-to-speech engine for lyrics) to fulfill those innermost desires.
I developed this project as Artist-in-Residence with Monochrome/Q21 at MuseumsQuartier in Vienna in August/September-2021, and presented at Roboexotica as part of Ars Electronica in September-2021.
This project uses:
- Raspberry Pi 4 Model B 8GB (with cooling fan added)
- 3 ArduTouch music synthesizer kits
- 3 FTDI-equivalent USB-Serial Cables
- 4-port USB hub
- openCV computer vision software
- eSpeak text-to-speech engine
- 4-channel stereo audio mixer, stereo audio amp/speakers
Here is a 15-minute video describing the project, and giving a demo of it in action:
https://youtu.be/23EKJEPwm7c
I am thankful for the super tutorial for installing OpenCV from Q-engineering
I am also super grateful for the great set of tutorials on using OpenCV for facial-recognition on Raspberry Pi from Adrian Rosenrock
And many thanks to the developers of eSpeak text-to-speech engine
Also, thanks to the great support from Monochrom and Q21 at the MuseumsQuartier in Vienna.
==================================================
==================================================
This project is Open Hardware
This work is licenses under the
Creative Commons Attribution-ShareAlike 4.0
CC BY-SA 4.0
To view a copy of this license, visit
https://creativecommons.org/licenses/by-sa/4.0/
==================================================
==================================================