Yesterday on Slashdot they reported about a new CAPTCHA. What is a Captcha you ask? You know those crazy little images of letters and numbers that you have to type in when you sign into some websites. You know the ones that old people like me can barely read and sometimes have to fill in two or three times? Those are CAPTCHAs.
Their purpose is to thwart the little web robots and script kiddies from hijacking websites and sending spam and the like. Unfortunately, the robots and script kiddies have been winning lately and it appeared it might be the end of the CAPTCHA. But low and behold the folks at Penn State - must be something about penn and geeks - have discovered a new way to deliver CAPTCHAs. They require the use of imagination. Something which most computers still lack. (And a few people as well.)
A user is asked to pass two tests: (1) click the geometric center of an image within a composite image, and (2) annotate an image using a word selected from a list. These images shown to the users have fake colors, textures, and edges, based on a sequence of randomly-generated parameters. Computer vision and recognition algorithms, such as alipr, rely on original colors, textures, and shapes in order to interpret the semantic content of an image. Because of the endowed power of imagination, even without the correct color, texture, and shape information, humans can still pass the tests with ease. Until computers can 'imagine' what is missing from an image, robotic programs will be unable to pass these tests.
What will they think of next?