Back to news

A Quick Guide to Face Recognition with AI

—Moji Solgi, Director of AI and Machine Learning

Published on


Microsoft's President, Brad Smith, recently published a set of principles around regulating the development and use of face recognition technologies. As an organization that takes ethical AI seriously, and as a close partner of Microsoft, we at Axon applaud Microsoft's thoughtfulness for taking this step.

Here we try to shed light on another dimension of the face recognition discussion that often gets overlooked. Face recognition is a broad term that lumps together a collection of technologies. This generalization can make conversations around the subject confusing. Below is an attempt to break down the components under the hood of what is referred to as facial/face recognition.

Algorithms vs. Data

AI algorithms involved in face recognition are not the true source of controversy around face recognition technology. It is the combination of some face recognition algorithms (especially face matching and face attributes) and databases for retention and face search that usually causes privacy and ethical concerns.


An algorithm is a sequence of steps executed by a computer that determines how to perform a task or solve a problem. Algorithms used for face recognition technologies (mostly machine-learned algorithms) can be one of the following:
*Note: the list below includes the major classes of face recognition technologies, but it is not comprehensive. For example, face verification and face alignment are excluded for simplicity.

Face Detection

In a given image, Face Detection finds faces and their locations. The Face Detection box in Fig. 1 highlights the detected faces in dotted boxes. Most commodity digital cameras, including mobile phones, run Face Detection to enhance image quality.

Face Tracking

In a given video, Face Tracking corresponds a face from one frame to the next consecutive frame. The Face Tracking box in Fig. 1 shows the face of one person being matched between two frames. This is useful for a police agency when they need to blur out an individual's face in a body-worn video that they want to release to the public. Note: tracking specific facial features (such as eyebrows, lips, etc.) is another area of research.

Face Re-identification

Face Re-identification is conceptually similar to Face Tracking, except the corresponding frames are not necessarily consecutive in the video. For example, if your face appears in the beginning of a video, and again at the end, Face Re-identification can recognize that it's the same face without identifying your face by comparing it to a database of faces.

Face Matching

Given a target face and a set of candidate faces, Face Matching finds which one of the candidate faces belongs to the target face. This is where algorithms meet databases for face search and retention. Some photo storage applications use Face Matching to tag a face that appears in various photos, and many smartphones use the technology to unlock your phone.

Face Attributes

Given an image or a video of a face, Face Attributes extracts information such as gender, ethnicity, emotions, age, facial landmarks, etc.


Data, in the case of face recognition, is a set of quantitative or qualitative values for reference. Commercial deployments of face recognition systems, such as systems you may see in airports around the world, generally reference a database of faces. These databases often include biographical information such as name, age, SSN, and more. In addition, the retention of the captured and/or extracted metadata in a database is a part of some of the face recognition systems.

What is Axon AI Doing

At Axon, we are currently working on algorithms for face detection, tracking, and re-identification. We use these algorithms for redaction in our Axon Evidence Redaction Studio, which helps our customers save time on the tedious task of obscuring and protecting an individual’s identity in a given body or in-car camera video that is released to the public.

A few projects Axon AI is currently working on include:

  • Vehicle Recognition, which is the ability to recognize the make, model, year, and color of vehicles on the road, to help law enforcement in scenarios that include finding missing children;
  • Speech Transcription, which is automatically converting speech to text, and eventually automating record keeping and data entry for police officers, eliminating manual paperwork;
  • Critical Event Recognition, which is when AI can detect an officer’s actions, such as a foot chase, that notifies other officers or the precinct that a critical event is unfolding.

We continue to discuss the development of these technologies with our AI & Policing Technology Ethics Board. The mission of this independent board is to provide expert guidance to Axon on the development of its AI products and services, paying particular attention to its impact on communities.