Digital Ugliness Detection

Usually, people associate facial recognition software with high-tech authentication techniques or auto-focusing aids in their digital cameras. Researchers at the Tel Aviv University decided to use recognition software blended with a learning parameter to teach a computer to identify beautiful people. The study relies on extrapolating common features from human ratings to create an algorithm that can replicate the rankings on previously unrated images. Programmer Amit Kagian explains, "Our software allows the computer to complete a much more complex task of [a]esthetic judgment, which humans cannot define exactly how they do it. [Ae]sthetic judgment is linked to sentiment and more abstract considerations, but now we have made the computer do it. This constitutes a substantial advance in the development of artificial intelligence." Amit's results with the machine [pdf] scores a Pearson correlation of 0.82 and a Spearman correlation of 0.83 during experiments that analyze such features as symmetry, "averageness," tone and facial artifacts.