Researchers at Carlos III University of Madrid (UC3M) have developed a facial biometrics system based on individual models. UC3M study author David Delgado Gomez says the objective is to create a model for each person that highlights the most distinguishing features on each face. Delgado says one way to describe a person is through traits that other people do not have, and their new system aims to apply that approach to an algorithm. The researchers say the most complicated part is combining facial geometry and facial texture. “With only the geometric information, very low classifications are obtained, which is why we combine this information with that of facial texture to obtain a more robust model, and a statistical way of combining them occurred to us, which offered very good results,” Delgado says. The researchers have shown that when their system is used in a controlled environment it can achieve 95 percent accuracy. The biggest challenge to facial-recognition systems is lighting, which can change the color of a person’s face. Aging also is a challenge as people’s faces can become heavier, thinner, or more wrinkled.
For More Information Visit: http://www.cpccci.com