project:picturethis

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
project:picturethis [2015/02/28 14:45] – [Story] tambergproject:picturethis [2018/04/24 10:55] (current) – [Links] alicesmith
Line 3: Line 3:
 A connected picture frame displaying historic images A connected picture frame displaying historic images
  
-===== Ideas Iterations ===== +{{https://farm9.staticflickr.com/8681/16672996925_ec53c13c61.jpg}}
-  - 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 :-) +
 ===== Story ===== ===== Story =====
  
-  * Our smart picture frame shows police photographs of homeless people by Carl Durheim (1810-1890)+  * The Picture This "smartframe 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   * 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)   * The algorithm detects gender, age and mood of the person on the portrait (not always right)
-  * You, as a spectator, become the judge / part of the system / algorithm+  * 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   * The person on the picture is at the mercy of the spectator, once again
  
 +{{https://farm9.staticflickr.com/8631/16485421338_40e86f1bce.jpg}}
 +{{https://farm9.staticflickr.com/8608/16671627211_074399694d.jpg}}
 ===== How it works ===== ===== How it works =====
  
-  * Picture frame has a camera doing face detection presence detection +  * Picture frame has a camera doing face detection for presence detection 
-  * Pictures have been pre-processed using an online cloud service+  * Pictures have been pre-processed using 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/
  
 +{{https://farm9.staticflickr.com/8608/16672997165_b32d138ee9.jpg}}
 +{{https://farm9.staticflickr.com/8577/16671979502_b6a4cc5bd0.jpg}}
 +{{https://farm9.staticflickr.com/8611/16673072845_aea4ee6a02_z.jpg}}
 ===== Questions (not) answered ===== ===== Questions (not) answered =====
  
Line 45: Line 39:
   * @tamberg   * @tamberg
   * and you   * 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 ===== ===== Material =====
Line 50: Line 58:
   * Raspi https://www.adafruit.com/products/998   * Raspi https://www.adafruit.com/products/998
   * 7inch TFT https://www.adafruit.com/products/947   * 7inch TFT https://www.adafruit.com/products/947
 +  * Picture frame http://www.thingiverse.com/thing:702589
  
 ===== Software ===== ===== Software =====
  
-  * http://www.raspberrypi.org/downloads/ => Raspbian+  * http://www.raspberrypi.org/downloads/ Raspbian
   * http://www.pygame.org - A game framework, allows easy display of images   * http://www.pygame.org - A game framework, allows easy display of images
-  * http://www.raspberrypi.org/facial-recognition-opencv-on-the-camera-board/ - OpenCV on Raspi-Cam+  * https://bitbucket.org/tamberg/makeopendata/src/tip/2015/PictureThis Scraper and Display
   * http://skybiometry.com/Demo   * http://skybiometry.com/Demo
 +  * http://qwikfix.co.uk/sky-customer-services/
 +  * http://simplecv.org
 ===== Links ===== ===== Links =====
  
   * https://pinboard.in/search/u:tamberg?query=glamhack   * 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
  
-{{tag>status:concept needs:dev needs:design needs:data needs:expert glam hardware}}+{{tag>status:demo glam hardware}}
  • project/picturethis.1425131102.txt.gz
  • Last modified: 2015/02/28 14:45
  • by tamberg