The Descriptive Camera created by Matt Richardson (@MattRichardson) as part of a Computational Camera class at New York University's Interactive Telecommunications Program takes an entirely new approach to photography and metadata by creating a device that turns your captured imagery into words via Amazon's Mechanical Turk service and a small networked thermal printer.
The camera consists of a USB webcam, a small thermal printer, shutter button, ethernet connection and Amazon's API. When a picture is taken it's sent off to the Turkers to create a written description of the image, which is then sent back to the camera and printed. According to Richardson's post the total processing time takes between three to six minutes and the cost of the service runs about $1.25 for each image that is eventually outputted for the user in a polaroid type format.
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.