How facial recognition works and how technology is evolving

What is facial recognition?

Facial recognition is a technology that automatically identifies (recognizes who is in the photo) or verifies (confirms that the person in the photo is that person) a person in a photo, video, or in person. For recognition, neural networks are used, which can read and analyze the unique features of a person’s face and compare them with the database.

These types of technologies are beginning to be used everywhere and even in licensed casinos in Spainabout which you can read reviews of online casinos.

How facial recognition technology has evolved

The first automatic facial recognition experiments were conducted in the 1960s by Woody Bledsoe, an artificial intelligence researcher at the University of Texas at Austin. His working group created a database with 800 photographs of people at different angles. The scientists then marked the faces with 46 coordinate points, using a modern tablet prototype. Using a special algorithm, the system displayed the faces at different angles, zooming in and out. In the second stage, the algorithm used 22 measurements, acting on the Bayesian decision theory, so that the global conclusion was as precise as possible. In the end, the system developed by Bledsoe was 100 times faster than a human.

In 1988, Michael Kirby and Lawrence Sirovic of Brown University applied the Eigenface approach using linear algebra to analyze images. They applied less than 100 different values ​​to mark the faces.

In 1991, Alex Pentland and Matthew Turk at MIT improved the Eigenfaces technique by incorporating environmental factors. They managed to automate the recognition process.

In the late 1990s, the US Defense Advanced Research Projects Agency (DARPA) and the National Institute of Standards and Technology published FERET, the largest database of faces: more than 14,000 images. It was initially used to find and identify criminals around the world, but was later made available to the public.

In 2010, Facebook began using facial recognition to find users in posted photos and offer to tag them.

In 2011, authorities in Panama and the United States launched a joint project called FaceFirst. It is a facial recognition technology that was used to disrupt illegal activities at the Tocumen airport in Panama. That same year, US police and intelligence agencies began using facial recognition to identify dead bodies, including that of Osama bin Laden.

Since 2014, facial recognition has been used in mobile phone cameras, and since 2017 in retail.

How does facial recognition work?

The technology is based on two neural networks:

The first is an alignment network. The software crops the detected faces (those that are too tight, turned in profile or just too small and blurry, the system may not recognize them). It then lines them up: detects the points for the eyes, nose, and mouth on the face. Lastly, rotate and resize the photo so that the points for the eyes, nose, and mouth are in specific places.

The second is a “recognizing” network. It feeds in an aligned image, fed by the first neural network, and outputs a face vector: a set of fixed-length numbers. These vectors may be different in different networks, but most often they are of some degree of two. The network produces similar vectors for similar faces and vice versa.

Huge databases of people’s faces are used to train neural networks. The input to the neural network tells it who the face belongs to, and it is then trained to give the most accurate results. After learning from millions of different people, the neural network begins to recognize new faces that were not in the database.

Where is facial recognition used?

Security

Automatic biometric identification systems (ABIS) are used by criminals, police and intelligence agencies to find criminals, prove crimes and prevent them, such as terrorist attacks or document fraud.

Facial recognition cameras are used for security at public events, for security checks at airports, and for access control in various organizations. The systems help find missing children, disoriented adults, or captives.

health and medicine

Facial recognition in hospitals and nursing homes helps to know if patients are taking their medication and to monitor their condition through a special monitor. Neural networks are even capable of detecting genetic diseases based on facial characteristics – such as DiGeorgey syndrome – and evaluating the general condition of the patient.

Commerce, hospitality and banking

Facial recognition technology helps identify customers and prevent fraud during in-store purchases, analyze customer behavior, and optimize service to sell more.

Online biometrics can be used to open an account and obtain credit, as well as to withdraw money from an ATM. For example, China’s KFC and America’s Amazon Go have “face pay.” In Russia, there are plans to introduce biometrics in major banks instead of the usual identification.

Education

Services based on facial recognition help during online learning: they make sure that students are not distracted during exams, do not cheat and do not use verbal cues.