Facial recognition technology works by measuring nodal points on faces such as the distance between the eyes and shape of cheekbones. These points are compared to a database of pictures to find a match. It is used in security systems and can identify people passing by cameras. While it provides security benefits, concerns include privacy issues with mass surveillance and systems being fooled by disguises or lighting/camera angle changes. Recent improvements have made algorithms over 100 times more accurate than in 1995 and able to outperform humans in some cases.