Picture This
connected frame with historic images
A connected picture frame displaying historic images
Story
- The Picture This “smart” frame shows police photographs of homeless people by Carl Durheim (1810-1890)
- By looking at a picture, you trigger a face detection algorithm to analyse both, you and the homeless person
- The algorithm detects gender, age and mood of the person on the portrait (not always right)
- You, as a spectator, become part of the system / algorithm judging the homeless person
- The person on the picture is at the mercy of the spectator, once again
How it works
- Picture frame has a camera doing face detection for presence detection
- Pictures have been pre-processed using a cloud service
- Detection is still rather slow (should run faster on the Raspi 2)
- Here's a little video https://www.flickr.com/photos/tamberg/16053255113/
Questions (not) answered
- Who were those people? Why were they homeless? What was their crime?
- How would we treat them? How will they / we be treated tomorrow? (by algorithms)
Data
- http://make.opendata.ch/wiki/event:2015-02
- http://make.opendata.ch/wiki/data:glam_ch
- https://commons.wikimedia.org/wiki/Category:Durheim_portraits_contributed_by_CH-BAR
Team
- @ram00n
- @tamberg
- and you
Ideas / Iterations
- Download the pictures to the Raspi and display one of them (warmup)
- Slideshow and turning the images 90° to adapt to the screensize
- Play around with potentiometer and Arduino to bring an analog input onto the Raspi (which only has digital I/O)
- Connect everything and adapt the slideshow speed with the potentiometer
- Display the name (extracted from the filename) below the picture
next steps, more ideas:
- Use the Raspi Cam to detect a visitor in front of the frame and stop the slideshow
- Use the Raspi Cam to take a picture of the face of the visitor
- Detect faces in the camera picture
- Detect faces in the images [DONE, manually, using online service]
- …merge visitor and picture faces
Material
- Raspi https://www.adafruit.com/products/998
- 7inch TFT https://www.adafruit.com/products/947
- Picture frame http://www.thingiverse.com/thing:702589
Software
- http://www.raspberrypi.org/downloads/ - Raspbian
- http://www.pygame.org - A game framework, allows easy display of images
- https://bitbucket.org/tamberg/makeopendata/src/tip/2015/PictureThis - Scraper and Display
- http://skybiometry.com/Demo
- http://qwikfix.co.uk/sky-customer-services/
- http://simplecv.org
Links
- https://pinboard.in/search/u:tamberg?query=glamhack
- http://press1for.co.uk/income-support-contact-number/
- http://www.open-electronics.org/raspberry-pi-and-the-camera-pi-module-face-recognition-tutorial/
- http://www.raspberrypi.org/facial-recognition-opencv-on-the-camera-board/ - OpenCV on Raspi-Cam
- https://speakerdeck.com/player/083e55006e4a013063711231381528f7 - Slide 106 for face replacement
- http://picamera.readthedocs.org/en/release-1.0/
Not used this time, but might be useful
- https://thinkrpi.wordpress.com/2013/05/22/opencv-and-camera-board-csi/ - old Raspian versions did not have the latest OpenCV installed. Nice howto for that
- https://realpython.com/blog/python/face-recognition-with-python/ - OpenCV, nice but not used
- http://docs.opencv.org - not used directly, only via SimpleCV
- http://makezine.com/projects/pi-face-treasure-box/ - maybe a nice weekend project
- https://learn.adafruit.com/creepy-face-tracking-portrait
- http://www.seeedstudio.com/depot/101LCD-Display-1366x768-HDMIVGANTSCPAL-p-1586.html - 10inch TFT
- http://www.aliexpress.com/item/FreeShipping-Banana-Pro-Pi-7-inch-LVDS-LCD-Module-7-Touch-Screen-F-Raspberry-Pi-Car/32246029570.html - 7inch TFT mit LVDS Flex Connector