Camera prints out description of what it sees

A New York University student has created a camera that can print out a textual description of the images that are taken with it.

The technology at the heart of Matt Richardson’s so-called Descriptive Camera is Amazon's Mechanical Turk API. This allows developers to submit Human Intelligence Tasks (HITs) for workers on the Internet to complete. In the case of the camera, the task is to describe what is found in an image.

For faster and cheaper results, the camera can also be put into "accomplice mode," where it will send an instant message to a specific individual. The instant message contains a link to the picture and a form where a the description of the image can be typed.

The camera itself is powered by the BeagleBone, an embedded Linux platform from Texas Instruments (Dallas, TX, USA). Attached to the BeagleBone is a USB webcam, a thermal printer from Adafruit (New York, NY, USA), a trio of status LEDs and a shutter button. The device connects to the Internet via Ethernet and is powered from an external 5V source.

After the shutter button is pressed, the photo is sent to Mechanical Turk for processing and the camera waits for the results. A yellow LED indicates that the results are still "developing" in a nod to film-based photo technology.

By setting the HIT price at $1.25, results are returned typically within 6 minutes and sometimes as fast as 3 minutes. The thermal printer outputs the resulting text in the style of a Polaroid print.

More information on the camera can be found here.

-- by Dave Wilson, Senior Editor, Vision Systems Design