Pareidoloop

Posted on 2012-08-08 in uncategorized

I ought to scribble down some words about pareidoloop (beyond those in the README at least), since it has been getting some attention recently.

Pareidoloop is a toy that makes images that approximate human faces. It starts by generating random polygons, feeding them into a computer vision face detection algorithm, and then continuing to add more polygons to increase the face detector’s “confidence” score.

Technically there’s nothing particularly interesting going on – all the hard work is done by Liu Liu’s Core Computer Vision library, which has a nice fast Javascript implementation (you can try it out here). The rest of it is just rendering random shapes, with a hill-climbing algorithm loosely based on Roger Alsing’s Evolution of Mona Lisa.

What has been interesting is people’s reactions to pareidoloop – for a quick experiment hacked together over a weekend, it has generated a lot of positive feedback and discussion. I guess this is down to the recognizable and sometimes spooky images that it generates, stimulating our primitive monkey brains’ hardwired tendency to see faces – the pareidolia from which it takes its name.

Written by phil on August 8th, 2012

Tagged with , ,

3 comments

3 Responses to 'Pareidoloop'

Subscribe to comments with RSS or TrackBack to 'Pareidoloop'.

  1. [...] Почитать подробности и посмотреть небольшую галерею с…. [...]

  2. Hi,

    I like to spend time on Hacker News. I saw your post several months ago. I bookmarked it.

    I created an E.P. recently and used some of the generated material from Pareidoloop.

    Is it okay to use the images? You can seem them at Vpena.com/sounds

    Let me know, I can always remove them.

    Thanks,
    Victor

    PS. I really dig the generator. It is a great tool.

    Victro

    12 Feb 13 at 12:39 am

  3. [...] (Erklärender Blogbeitrag) [...]

Leave a Reply