A team headed by Prof. Daniel Cohen-Or of the Tel Aviv University (TAU) computer studies department that included colleagues at King Abdullah University in Saudi Arabia, has developed a ‘synthesis technique’ to overcome the computer automatons or ‘bots’ that can get into sites and vote, open financial accounts or otherwise influence content.
Internet users often have to identify and key in a collection of distorted letters and numbers to gain entrance to various Web sites. These are called Capthcha, and are intended as a barrier to prevent bots from getting into sites.
An international team headed by TAU and including researchers from the Saudi university, the University of Delhi in India and researchers in Taiwan has generated images of animated 3-D objects that are detectable by humans but difficult for an automatic algorithm to recognize.
The images are based on ’emergence’ – the unique human ability to aggregate information from seemingly meaningless pieces and perceive a meaningful whole. This special skill of humans can constitute an effective way to tell humans and machines apart, says Cohen-Or.
The new technique allows the generation of an infinite number of images with 3-D ’emergence figures,’ that computer vision algorithms are incapable of effectively processing.
While promising, Cohen-Or says the technique must be developed further before it can be of practical use.