Incredible DIY Camera Outputs Description Of Image Rather than Photograph
This is a DIY descriptive camera. A what? A camera that takes descriptions of images rather than photographs. That’s right rather than take images of objects it outputs a description of the image you’re looking at. It was developed by Matt Richardson and is powered by the Amazon Mechanical Turk crowdsourcing API. So how does it work? Well you take the photo, someone, somewhere, on the Internet sees the photo, describes what you’re looking at in a few brief words and the text is sent back to the camera for printing on a thermal printer. All in all it takes about 3 to 6 minutes.
Here’s what Matt Richardson has to say about his camera;
Modern digital cameras capture gobs of parsable metadata about photos such as the camera’s settings, the location of the photo, the date, and time, but they don’t output any information about the content of the photo. The Descriptive Camera only outputs the metadata about the content. As we amass an incredible amount of photos, it becomes increasingly difficult to manage our collections. Imagine if descriptive metadata about each photo could be appended to the image on the fly—information about who is in each photo, what they’re doing, and their environment could become incredibly useful in being able to search, filter, and cross-reference our photo collections. Of course, we don’t yet have the technology that makes this a practical proposition, but the Descriptive Camera explores these possibilities.
Not sure what practical use it has but I’d love to get my hands on one if only to test peoples description skills…
Via Laughing Squid
190 total views, 1 today
