All about Facial Recognition Technology

Srinivas Chintakindi, Manager – Technology/Products at PamTen

What is Facial Recognition?

Facial recognition is the least intrusive and fastest growing fields of biometric technology. Biometrics in general is the body’s measurements and calculations – the metrics of the human body and characteristics.  The study of the body’s measurements and relationships goes back throughout human kind, but the technology to quantify it has been significantly advanced by current technology.

There are several forms of biometric technology:

• Retinal and/or Iris scans
• Fingerprint recognition
• Palm scan
• DNA matching
• Facial Recognition

Focusing on Facial Recognition, with the latest developments in technology, systems are now able to identify a person’s face and verify who that face belongs to from any digital image.

How does it work?

Facial recognition analyzes the characteristics of a person’s face through input of a digital image. It measures the overall facial structure, including certain measurements of distance and depth that create the hills, peaks, and valleys of a face. These measurements are retained in a database as a faceprint and are compared when a user stands before the camera or sends another digital image. It is estimated that biometric facial recognition technology will soon overtake fingerprint biometrics as the most popular form of security for user authentication. Currently, Apple’s iPhone X and some Android phones include Face ID technology that lets users unlock their phone with a Faceprint mapped by the Phone’s camera.

There are a variety of facial recognition methodologies, but in general, they work by comparing selected facial features from the given image with already stored facial data within a data source. When the image is fed into the software, it maps the individual’s facial features mathematically and stores the data as a faceprint. Then the software uses machine/deep learning algorithms to compare a live capture or digital image to the stored faceprints to verify an individual’s identity.

Every face has numerous, distinguishable landmarks; the different peaks and valleys that make up unique facial features. Each human face has approximately 80 nodal points that are measured for verification’s. Some of these measured by the Facial Recognition Technology are:

• Distance between the eyes
• Width of the nose
• Distance between nose and lips
• Depth of the eye sockets
• The shape of the cheekbones
• Eye shape
• Skin texture
• The length of the jaw line

These nodal points are measured creating a numerical code, the faceprint, representing the face in the database.

Have you posted a picture to Facebook and noticed that the system often automatically asks if you’d like to tag other friends that are in the picture? That’s because Facebook uses facial recognition software to tag individuals in photographs. Each time an individual is tagged in a photograph, the software stores mapping information about that person’s facial characteristics. Once enough data has been collected, the software can use that information to identify a specific individual’s face when it appears in a new photograph. As the largest social media platform in the world, it’s building quite an extensive data base of faces.

What Can It Be Used For?

Facial recognition is getting more popular and being used in many commercial and governmental industries. Below are some of examples of how facial recognition is currently being used.

• Law enforcement is using this software more frequently for a variety of reasons: to scan crowds for wanted men and women, check suspects against mug shots, and protect the nation borders. It can also be used to find missing children and victims of human trafficking. In the event of missing child or person, their image can be added to the database and security systems at public places like airports, train stations, and bus terminals that can scan the crowd continuously. It can alert the law enforcement if any matching Face is found.
• For large events and concerts, facial recognition software can be used to identify the guests at the gate and can decide whether the person purchased the tickets for that event or not. If they did it can check-in the guest automatically.
• Facial recognition can be used to diagnose diseases that cause detectable changes in appearance.
• Face recognition is currently being used to instantly identify when known shoplifters, organized retail criminals, or people with a history of fraud enter retail establishments. Photographs of individuals can be matched against large databases of criminals so that loss prevention and retail security professionals can be instantly notified when a criminal that prevents a threat enters a store.
• Dating sites match the people with similar features, because some people are most attracted to those that look like them.
• Social media sites use this technology to tag the people automatically every time images are uploaded.
• Casinos can use the facial recognition software to help addictive gamblers. It can also help the casinos by identifying the cheaters or advantage gamblers. It can identify members of voluntary exclusion lists and alerts the casinos. These people can cost casinos big fines if they are caught gambling. Along with casinos, bars can also use this technology to identify the underage drinkers.
• Mobile companies can use the Face as an authentication mechanism to unlock a phone or smart mobile device. Mobile purchases can also be purchased with facial recognition.
• Face recognition surveillance systems can instantly identify when expelled students, dangerous parents, drug dealers, or other individuals that pose a threat to school safety enter school grounds. By alerting school security guards in real time, face recognition can reduce the risk of violent acts. In addition to make the schools/universities safer, this technology can also be used to take the student attendance automatically.
• Advertising companies can use Facial recognition technology to identify the age and genders of people by making educated guesses based on previous biometrics and provide targeted advertisements in open spaces like gas stations.
• Face recognition can work as a means of access control to ensure that only authorized individuals get into facilities like labs, boardrooms, bank vaults, training centers for athletes, and other sensitive locations.

Facial recognition technology has many positive applications. But it also raises many questions about personal privacy and governmental and commercial intrusion. How do you feel about the growing incorporation of facial recognition technology in our lives?