element14 Community
element14 Community
    Register Log In
  • Site
  • Search
  • Log In Register
  • About Us
  • Community Hub
    Community Hub
    • What's New on element14
    • Feedback and Support
    • Benefits of Membership
    • Personal Blogs
    • Members Area
    • Achievement Levels
  • Learn
    Learn
    • Ask an Expert
    • eBooks
    • element14 presents
    • Learning Center
    • Tech Spotlight
    • STEM Academy
    • Webinars, Training and Events
    • Learning Groups
  • Technologies
    Technologies
    • 3D Printing
    • FPGA
    • Industrial Automation
    • Internet of Things
    • Power & Energy
    • Sensors
    • Technology Groups
  • Challenges & Projects
    Challenges & Projects
    • Design Challenges
    • element14 presents Projects
    • Project14
    • Arduino Projects
    • Raspberry Pi Projects
    • Project Groups
  • Products
    Products
    • Arduino
    • Avnet Boards Community
    • Dev Tools
    • Manufacturers
    • Multicomp Pro
    • Product Groups
    • Raspberry Pi
    • RoadTests & Reviews
  • Store
    Store
    • Visit Your Store
    • Choose another store...
      • Europe
      •  Austria (German)
      •  Belgium (Dutch, French)
      •  Bulgaria (Bulgarian)
      •  Czech Republic (Czech)
      •  Denmark (Danish)
      •  Estonia (Estonian)
      •  Finland (Finnish)
      •  France (French)
      •  Germany (German)
      •  Hungary (Hungarian)
      •  Ireland
      •  Israel
      •  Italy (Italian)
      •  Latvia (Latvian)
      •  
      •  Lithuania (Lithuanian)
      •  Netherlands (Dutch)
      •  Norway (Norwegian)
      •  Poland (Polish)
      •  Portugal (Portuguese)
      •  Romania (Romanian)
      •  Russia (Russian)
      •  Slovakia (Slovak)
      •  Slovenia (Slovenian)
      •  Spain (Spanish)
      •  Sweden (Swedish)
      •  Switzerland(German, French)
      •  Turkey (Turkish)
      •  United Kingdom
      • Asia Pacific
      •  Australia
      •  China
      •  Hong Kong
      •  India
      •  Korea (Korean)
      •  Malaysia
      •  New Zealand
      •  Philippines
      •  Singapore
      •  Taiwan
      •  Thailand (Thai)
      • Americas
      •  Brazil (Portuguese)
      •  Canada
      •  Mexico (Spanish)
      •  United States
      Can't find the country/region you're looking for? Visit our export site or find a local distributor.
  • Translate
  • Profile
  • Settings
PiCasso Design Challenge
  • Challenges & Projects
  • Design Challenges
  • PiCasso Design Challenge
  • More
  • Cancel
PiCasso Design Challenge
Blog PiCasso Adapting Art to Viewers: Introduction, Blog #1
  • Blog
  • Forum
  • Documents
  • Polls
  • Files
  • Events
  • Mentions
  • Sub-Groups
  • Tags
  • More
  • Cancel
  • New
  • Share
  • More
  • Cancel
Group Actions
  • Group RSS
  • More
  • Cancel
Engagement
  • Author Author: fmilburn
  • Date Created: 17 Mar 2019 9:07 PM Date Created
  • Views 2204 views
  • Likes 15 likes
  • Comments 11 comments
  • picasso
  • image recognition
  • rasperry pi camera v2
  • raspberry pi 3b+
  • ai
  • art
  • picasso_design_challenge
  • pi face
Related
Recommended

PiCasso Adapting Art to Viewers: Introduction, Blog #1

fmilburn
fmilburn
17 Mar 2019

Introduction

 

Note:  This is the original introduction to the project.  There is a summary which may be a better starting place for those wishing to understand the project here: PiCasso Adapting Art to Viewers: Conclusion, Blog #11

PiCasso Adapting Art to Viewers: Conclusion, Blog #11

Art is often made to appeal to specific age groups - usually adults.  Adapting Art to Viewers will explore the idea of using AI to recognize the viewer and adapt the art to their age or interests.  The art work will thus encourage early art appreciation and be attractive to a wider audience.

image

This is the first post in a series and describes the project objectives and lays out a plan for achieving them.

 

Resources

Kit Supplied to Challengers

  • Raspberry Pi Model 3 B+
  • Starter Kit
  • PiFace Digital 2: animatronics
  • Raspberry Pi Camera V2: detection of faces

Additional Hardware

  • Raspberry Pi 7" Touchscreen Display: art display
  • Motion Detection Sensor: detection of distance and movement
  • Motors, Lights, etc.: provide interest for young children

Software

  • Raspbian
  • Python: detection, display, animatronics
  • OpenCV:  detection of faces and possibly age

 

The resource list is expected to change as the project progresses.  For example, face detection on the Raspberry Pi is computationally extensive and it may be necessary to dedicate one Raspberry Pi solely to AI and use another for the artistic display and actions.  Additional sensors, software, and output devices may be added as the project advances.

 

Simplified Block Diagram

image

Ideas to Explore

  • Display lights, shapes, sounds and animatronics using PiFace for very young viewers
  • Display self made art of older children, or favorite art / comics they choose themselves
  • Favorite art or photographs for adults
  • Music and sound
  • User input to change the display or sound
  • Detection and beckoning of the viewer closer
  • Enclosure or frame that looks good in the home

 

Project Plan

The project will be divided into phases and progress reports made weekly.  Each phase is expected to last approximately 2 weeks.

  • Phase 1: setup and test the hardware and software.
  • Phase 2: design project framework, art modules, and recognition software
  • Phase 3: create early childhood art module with focus on lights, shapes, sounds and movement
  • Phase 4: develop art for children module with ability to display their own art and exposure to suitable art of others
  • Phase 5: produce art for teens and adults module
  • Phase 6: complete project.

 

Additional Thoughts

While the project is aimed at demonstrating how AI can adapt art to a varied audience, the concept could be expanded to other household applications.  For example, a "magic mirror" could recognize school children and remind them to take their uniform for after school activities, or bring up the weather and train schedule for an adult heading off to work.  Thanks for reading and as always thoughts and upgrades are appreciated.

 

Other Blogs in this Series

PiCasso Adapting Art to Viewers: Introduction  Blog #1

PiCasso Adapting Art to Viewers: OpenCV Face Detection, Blog #2

PiCasso Adapting Art to Viewers: Cabinet Design, Blog #3

PiCasso Adapting Art to Viewers: Pi talks to Pi, Blog #4

PiCasso Adapting Art to Viewers: Grandpa Shark, Blog #5

PiCasso Adapting Art to Viewers: More on Cabinet Design, Blog #6

PiCasso Adapting Art to Viewers:  New Art, Blog #7

PiCasso Adapting Art to Viewers:  Mechanical Complete, Blog #8

PiCasso Adapting Art to Viewers:  Displaying Art, Blog #9

PiCasso Adapting Art to Viewers:  Demonstration, Blog #10

PiCasso Adapting Art to Viewers: Conclusion, Blog #11

  • Sign in to reply

Top Comments

  • genebren
    genebren over 6 years ago +6
    Frank, Very interesting! You have quite a bit of technology stuffed into your project plans. I look forward to seeing your progress as you work through your plan. Good luck! Gene
  • 14rhb
    14rhb over 6 years ago +4
    Hi Frank, A great concept - I'll look forward to following your progress. Rod
  • fmilburn
    fmilburn over 6 years ago in reply to shabaz +4
    Thanks Shabaz, I am curious to see how quickly and accurately OpenCV will identify people on the Pi. I received the kit today from element14 so have just started.
  • kiri-ll
    kiri-ll over 6 years ago in reply to fmilburn

    Ah, so you recognize the known users. That's a good way! Now it sounds realistic image I am excited to see the updates on this blog!

    • Cancel
    • Vote Up +4 Vote Down
    • Sign in to reply
    • More
    • Cancel
  • fmilburn
    fmilburn over 6 years ago in reply to kiri-ll

    As noted above, I will use OpenCV for the AI.  It is not real quick or particularly accurate as I have it currently implemented, but seems sufficient for a demonstration of the concept.  Representative faces are put into separate named folders and OpenCV "learns" from the samples.  When it detects a face it places a rectangle around it and marks it as either recognized (using the name on the folder containing the learning samples) or unrecognized.

     

    My first pass will be to place members of the household in the folders.  When it is a recognized face I will display their interest.  Longer term it would be interesting to see if it can be trained to recognize unknown persons by age or other characteristics but that would definitely be a stretch goal for this competition.

    • Cancel
    • Vote Up +3 Vote Down
    • Sign in to reply
    • More
    • Cancel
  • kiri-ll
    kiri-ll over 6 years ago

    > using AI to recognize the viewer and adapt the art to their age or interests

     

    Which AI algorithms do you plan to use? Can OpenCV classify age by faces? How do you classify interests by faces?

    • Cancel
    • Vote Up +3 Vote Down
    • Sign in to reply
    • More
    • Cancel
  • fmilburn
    fmilburn over 6 years ago in reply to shabaz

    Thanks Shabaz,

     

    I am curious to see how quickly and accurately OpenCV will identify people on the Pi.  I received the kit today from element14 so have just started.

    • Cancel
    • Vote Up +4 Vote Down
    • Sign in to reply
    • More
    • Cancel
  • fmilburn
    fmilburn over 6 years ago in reply to DAB

    Thanks!

    • Cancel
    • Vote Up +2 Vote Down
    • Sign in to reply
    • More
    • Cancel
>
element14 Community

element14 is the first online community specifically for engineers. Connect with your peers and get expert answers to your questions.

  • Members
  • Learn
  • Technologies
  • Challenges & Projects
  • Products
  • Store
  • About Us
  • Feedback & Support
  • FAQs
  • Terms of Use
  • Privacy Policy
  • Legal and Copyright Notices
  • Sitemap
  • Cookies

An Avnet Company © 2025 Premier Farnell Limited. All Rights Reserved.

Premier Farnell Ltd, registered in England and Wales (no 00876412), registered office: Farnell House, Forge Lane, Leeds LS12 2NE.

ICP 备案号 10220084.

Follow element14

  • X
  • Facebook
  • linkedin
  • YouTube