Facial Recognition

Facial recognition is a category of biometric software system that maps a person's facial features mathematically and stores the information as a faceprint. The software system uses deep learning algorithms to check a live capture or digital image to the hold on faceprint in order to verify a person's identity.

How a facial recognition application works ?

The software identifies 80 nodal points on a human face. In this context, nodal points are endpoints used to measure variables of a person’s face, such as the length or width of the nose, the depth of the eye sockets and the shape of the cheekbones. The system works by capturing information for nodal points on a digital image of an individual’s face and storing the resulting information as a faceprint. The face print is then used as a basis for comparison with data captured from faces in an image or video.

Even though the facial recognition system solely uses 80 nodal points, it will quickly and accurately determine target people once the conditions are favorable. However, if the subject’s face is partially obscured or in profile rather than facing forward, this type of software is less reliable. According to the National Institute of Standards and Technology (NIST), the incidence of false positives in facial recognition systems has been halved every two years since 1993.

Who uses facial recognition?

• U.S. government at airports.
• Mobile phone makers in products
• Colleges in the classroom
• Social media companies on websites
• Airlines at departure gates