Object recognition-powered games

I didn’t really have much time for this, but still wanted to quickly put together a demo just to throw this idea out there.

I just finished one of two demos I’m working on and would like to hear some feedback.

For this demo, the objective is to identify countries based on their capital cities. So for example the capital will be Budapest. You will have to look up a picture of the flag of Hungary and drag it into the browser window on the timer before it runs out and the next city is revealed.

A few notes:

  • this is pre-alphaproof of concept stuff – only tested in two three browsers (Chrome and Firefox on Linux and Opera on Windows 7…or 8)
  • I am using a 3rd party image detection API, it works pretty well, but only accepts JPGs, PNGs and GIFs – most of searches for country flags lead to Wikipedia where they use SVGs, so you are better off directly searching for “italian flag jpg
  • you will need to open the image in your browser directly – that is click all the way to the website where the image is, right-click -> Open image in a new tab (or something similar, depending on your browser) and then drag it on the timer
  • I’m thinking about expanding this demo into a little quiz game where the player could choose from several categories (capital cities, monuments, traffic signs etc)
  • the first demo that I mentioned I’m working on is put on hold while I’m waiting for another API to update to include their new concept recognition (which should be soon, as I was told)

Here is the link for the demo. Enjoy!

More from the blog

A tinted, zoomed in screenshot of a JSON object showing server information about a Mastodon instance.
A tinted screenshot of an unlabeled scatter chart, with most data points grouped on the right.
A tinted screenshot of two charts, one showing the popularity of various fediverse platforms (with Mastodon far ahead of the rest), and the other chart showing distribution of domain creation dates, mostly clustered around 2023.

📖 Visit blog