Digital Citizenship

Understanding the Basics of Facial Recognition Technology

Biometric security was first commercially introduced to the digital world with the use of fingerprint technology which was to a large extent, grouped under digital forensics. This technology has thrived but can definitely be improved in many ways. Facial recognition technology takes care of the majority of its drawbacks with its ability for remote verification, ease of use, and affordability.

Photo by Ryan Miguel Capili from Pexels

Working Principles of Facial Recognition Technology

The facial recognition system can be implemented in two major ways. The basic form is 2D imaging which uses flat images from pictures. This is rather inaccurate as the software can easily be fooled by properties such as angles and shadows. 3D imaging, a more advanced system, uses a web of infrared lights that mark every facial characteristic.

This web of lights is then sent through the camera to the software. The pixels will then be converted into a numeric code. This code is then compared with other stored values in the database in order to make a match. On a more advanced and complex level, some systems use the surface texture analysis technique which focuses on skin properties such as wrinkles and distance between skin pores to accurately make a match.

As with most applications that deal with Artificial Intelligence and Machine Learning, the more the raw data used to train the algorithms, the more accurate the result. Hence, virtually every facial image picked up by facial recognition software ends up getting saved to a database.

From the technical point of view, facial recognition works based on the geometry of the facial attributes such as:

  • the shape of the face
  • distance between the eyeballs
  • depth of the eye sockets
  • width of the nose
  • jawline structure

When these attributes are put together, they form a facial signature. This puts the technology under the biometrics field since the details generated are peculiar to every human being – just like their fingerprint and iris structure.

Facial Recognition Used in Various Sectors

This technology has found its way into a couple of sectors. Explained below are some of the ways facial recognition technology is making waves:

Law Enforcement: The primary benefit of facial recognition technology in this regard is for the detection and prevention of criminal activities. Apart from its obvious use in policing, this technology is used for issuance and identification of identity documents in order to prevent any form of identity fraud. Face match is also used in carrying out security missions in public places. Such a use case presents itself when there is a potential security threat at a large gathering or to find missing adults or children.

Health: With respect to health, significant advancement has been made in this area. With the use of this technology:

  • a patient’s use of medication can be appropriately tracked;
  • pain management procedures can be administered and;
  • genetic diseases such as DiGeorge syndrome can be detected. This has a success rate of 96.6%.

Retail Shopping: Although one of the least areas that would be expected to use such technology so soon, retail outlets have begun using facial recognition in marketing processes in order to improve customer experience. Stores in the US such as Amazon GO and Saks Fifth Avenue are reportedly using such technology.

Nothing is Completely Free

Nothing good comes entirely free – not especially with respect to technology that deals with data and privacy. In the quest for a large number of facial images used to train algorithms, governments and institutions often create lopsided agreements or employ the use of illicit methods in order to obtain this data, which has paved way for facial recognition protests in the US.

Unknown to many, Facebook has a facial recognition feature turned on for users and this would most likely help them train their models. In order to keep personal data safe, you can turn this feature off. It is also advisable that everyone reads privacy policies properly and take proper precautions when performing online activities on websites that collect user data.

Chris Jones @TurnOnVPN