Unusual camera turns your images into words

Before all the Instagram and Pintrest users start to panic, let's clarify. This camera doesn't do away with your images — it is a device that sends your captured image to humans who then describe your photo in words.

I love the idea of having someone translate a photographic image into words. Like Forrest Gump's mama used to say, "[It's] like a box of chocolates…you never know what you're going to get."

The "Descriptive Camera" is a USB webcam, a shutter button, a small thermal printer and an Ethernet connection. When a user snaps a photo, it's sent via Amazon's Mechanical Turk API to humans who create a written description. They then send the description back to the camera and their text is printed via the thermal printer, framed in a printed border that mimics a Polaroid style frame.

The written result could be as varied as "This is a faded picture of a dilapidated building. It seems run down and in need of repairs" to It's a dark room with a window. The image is quite pixelated."

The Descriptive Camera is the creation of Matt Richardson, as part of a class for New York University's Interactive Telecommunications Program.

According to his website, Richardson notes that the Amazon Human Intelligence Task (HIT) — or description of the image — costs about $1.25 for each image and takes around three to six minutes to complete. While the camera is obviously in the early stages he's already built in a feature that allows the camera to send out links to the image via instant messenger, widening and cheapening the potential written interpretation.

Other plans for the device include upgrading from the external 5-volt power source to self-contained batteries and providing for wireless data. With those enhancements creating portability, this camera with its unique view on the world could take off.

For those interested in the how-to side of Richardson's project, he's created a full run down of equipment and techniques used on his website. You'll also find samples of images and their "text picture" counterpart that is totally fascinating.

Apparently beauty is not just in the eye of the beholder, but also how the beholder and interpret that image into words.

Matt Richardson, via The Verge

For the latest tech stories, follow DVICE on Twitter
at @dvice or find us on Facebook