What Is Facial Recognition?

Written by Coursera Staff • Updated on

Facial recognition is an increasingly common tool for verifying someone's identity. Learn more about what is facial recognition and its applications in different industries.

[Featured Image] A man uses facial recognition to get into his office.

Facial recognition is a system used to identify a person by analyzing the individual's facial features, and the term also refers to the software that automates the process. It scans the person's face, notes key characteristics, and compares it to another image stored in a database. If the images match, the system confirms the identity. 

The practice of using images to identify people dates back at least 150 years when law enforcement agencies started taking photographs of people in custody. They used the photos to record who was in prison and could distribute the pictures when someone escaped. Technological advances, including biometrics, artificial intelligence, and machine learning, have helped increase accuracy and created a market worth more than $5 billion in 2022 [1].

Today, you can find facial recognition software used in many different industries, including retail, banking, and transportation. As the field grows, so do job opportunities directly and indirectly related to the technology. In this article, we'll explore facial recognition, how organizations use it today, and some of the careers you can pursue in this field.

Types of facial recognition

Two broad categories used to classify facial recognition software are holistic and feature-based, terms describing the process used to analyze faces. Holistic models examine your entire face and compare your features to those in images stored in a database. A feature-based model analyzes your face more deeply—for example, considering measurements between features and the contours of bones.

You also can sort facial recognition by the techniques used to capture an image. If you're using a camera-based model, you take a picture of yourself using the camera on your device. Each time you attempt to unlock the device, you turn on the camera and let the software compare the live image to the stored image to verify your identity. Infrared-based models work similarly, but they use infrared sensors to capture a 3D image of your face. An important advantage of this model is that the cameras work in dim light and are more secure.

How facial recognition works

Facial recognition software typically follows a three-step process: detection, analysis, and recognition.

  • Detect: In the first step, the program searches through an image looking for facial data. It views faces from the front and side, looking for distinctive features to analyze in the next step.

  • Analyze: After identifying a face in an image, the program examines facial landmarks like the distance from the chin to the forehead and between the eyes. It also considers the shape of different features like the cheekbones, lips, ears, and more.

  • Recognize: In the final step of the process, the facial recognition program applies what it's learned from the data to verify an individual's identity. It may compare the current image under analysis with a stored image like one used on a government ID.

What is facial recognition used for?

Facial recognition software has multiple uses, including protecting access to sensitive information, confirming identity, and preventing fraud. What was once only seen in sci-fi flicks now has applications in your daily life. The following list highlights some ways you may see people and organizations using facial recognition technology:

  • Access control: Verify identity before granting access to devices, buildings, and documents.  

  • Attendance: Scan people as they enter a facility to create an attendance record for work or school. 

  • Banking: Confirm a customer's identity at ATMs and banking centers to prevent fraud.

  • Customer experience: Notify authorities when known shoplifters are in stores, suggest products for customers, and allow customers to pay for purchases. 

  • Health care: Improve infection control by reducing the number of touchpoints in a facility, identify genetic diseases, and monitor patients.

  • Investigations: Assist detectives during investigations and ensure officers have arrested the correct individuals.

  • Security: Confirm the identity of individuals, track movements, and prevent unauthorized access to sensitive locations and equipment. 

  • Transportation: Verify passengers' identity at airports and border crossings to increase convenience and security. 

Who uses facial recognition?

Several types of organizations use facial recognition software to confirm a person's identity, including law enforcement and banks. Personnel working in airports and border control may use facial recognition to verify the identity of individuals traveling and entering the United States. Cell phone and computer users may rely on facial recognition capabilities to restrict device access and protect sensitive information. Some retailers and bankers install facial recognition systems to customize the customer experience and prevent theft. 

Pros and cons of using facial recognition

Fans of facial recognition typically appreciate the convenience it offers, while less enthusiastic people may raise questions about privacy. However, the benefits and drawbacks of using facial recognition extend beyond these top points. Here are more pros and cons of using facial recognition.


Facial recognition offers several advantages over other biometric screening and access control types. It tends to be quicker and easier to use than fingerprint analysis or retina scans—capturing your face in the camera lens is usually less complicated than lining up your fingertip on a device's scanner. Facial recognition is usually more secure than passwords and PINS, which someone can guess, and it has greater accuracy than other authentication methods like phone numbers and email addresses. Facial recognition technology often integrates more easily with existing security software.


Privacy is one of the top concerns surrounding facial recognition, and several states have passed laws restricting where organizations can use the software and what they do with the data they collect from it. The threat of a data breach is troublesome because facial features cannot be changed like a password or PIN, increasing the danger of identity theft if someone has access to facial recognition data. Some organizations have raised questions about the accuracy of facial recognition software, as others have noted the software sometimes has problems confirming the identity of individuals with darker skin. This issue can lead to a greater number of false positives. 

How to get started in facial recognition

Your first steps toward a career in facial recognition depend on the type of work you want to do. For example, you may learn how to code if you want to design facial recognition software. This means your path toward a career in facial recognition will likely look different from someone else's. Fortunately, the future of the facial recognition market looks promising. It should continue to grow over the next few years, and analysts anticipate a value of $7 billion by 2026 [2].

A facial recognition analyst makes an average of $71,792 annually, and you'll likely need a graduate degree and specialized training to qualify for this job [3]. You also can find more career options in the field. The following list highlights the variety of facial recognition jobs available and salary details.

  • Image processing engineer: $117,310 [4]

  • Machine learning engineer: $127,712 [5]

  • Pattern recognition engineer: $130,559 [6]

  • Software developer: $106,730 [7]

  • Software sales: $109,139 [8]

  • Visualization artist: $95,779 [9]

Getting started with Coursera

If your experience with facial recognition is using it to open your smartphone, a beginner-friendly course like Machine Learning for All can be a great place to start learning about the algorithms powering the technology. If you have more experience, consider the Deep Learning Specialization, which includes a course in convolutional neural networks, one of the models used in face recognition. You can find these courses and more on Coursera.

Article sources

Keep reading

Updated on
Written by:

Editorial Team

Coursera’s editorial team is comprised of highly experienced professional editors, writers, and fact...

This content has been made available for informational purposes only. Learners are advised to conduct additional research to ensure that courses and other credentials pursued meet their personal, professional, and financial goals.