We collected every email and every tweet from the 2020 Democratic primary.
What we found might surprise you.

Facing the Reality of Facial Recognition: The Good and the Bad

Mara Calvello
Mara Calvello  |  October 15, 2019

The color of your eyes. The slope of your nose. The shape of your lips.

These are all elements that make you, you. These unique qualities of your face are also what facial recognition technology uses to pick you out of a crowd.

While facial recognition was once something only seen in Sci-Fi movies, it is now a part of our daily lives. And whether we like it or not, it’s here to stay.

While Hollywood loves including facial recognition as a plot-point in media, movies and television haven’t done a great job explaining how facial recognition software actually works.

Facial recognition uses a combination of biometrics software applications, artificial intelligence, 3D mapping, and deep learning to compare and analyze patterns based on someone’s face. Although it’s mostly used for security and surveillance purposes, there is increasing interest across various markets, as well as use for the everyday consumer, especially as it gets more secure, advanced, and reliable.

How does facial recognition work?

There’s no denying that facial recognition is an advanced form of technology, but how does it work, exactly? There are essentially three components that make it work.

  1. The face detection process, which identifies and locates the human face in images and videos.
  2. The face capture process, which converts analog information, like the face, into a set of digital information based on specific facial features.
  3. The face match process, which verifies if two faces belong to the same person.

Facial recognition technology

The image recognition technology used to identify facial features is an essential part of making it work correctly and efficiently. It’s no easy task to pick a face out of a crowd and compare it to a database of stored images.

For this software to work, it has to be able to distinguish between a basic face and the rest of the background, while also measuring the various features of the face. To do this, the software analyzes over 80 elements, also called nodal points, of the human face.

  • Distance between the eyes
  • Width of the nose
  • Shape of the cheekbones
  • Depth of the eye sockets
  • Length of the jawline

 

These points are measured by creating a numerical code, otherwise called a faceprint, that will represent a face within a database.

Related: Interested in image recognition software but unsure which one to choose? Check out our list!

See the best Image Recognition Software on the market →

There’s also new technology emerging that uses skin biometrics, which is the uniqueness of the skin texture, for even more accurate results. This type of software creates a skinprint that will analyze any lines or pores within the texture. Skin biometrics will also help to find differences in identical twins, which is not yet possible using facial recognition alone.

Facial recognition software

Using artificial intelligence, facial recognition software is able to detect human faces in real-time. This software turns images into data in the sense that they are inputted into an algorithm, which then outputs a solution. This solution can be either tagging a person in a photo or identifying a suspect in a crime. 

This type of software is making waves throughout society as it's used in more industries and markets than ever before. Most facial recognition software programs are able to:

  • Provide a deep learning algorithm for facial recognition
  • Connect with image data pools identify specific faces based on various features
  • Consume the image data as an output and provide an outputted solution 

Learn more: Find out even more about what facial recognition can do with these 22 facial recognition statistics!

Read more: 22 Facial Recognition Statistics  →

Examples of facial recognition

As facial recognition becomes such a staple in society, you’ll find it in more places than you may think. And no, not just on your phone.

DeepFace

Created by Facebook, this facial recognition system can identify human faces in pictures uploaded to the social media platform with up to 97% accuracy. Each time a Facebook user is tagged in a photograph, DeepFace maps information about their facial characteristics. When enough data is collected, the software can identify a specific person in a new photograph.

For example, when I upload a new photo to Facebook of myself and one of my family members, DeepFace prompts me to tag them automatically.

Example of Facebook's DeepFace

FaceNet

In June 2015, Google unleashed FaceNet, which is used on the Labeled Faces in the Wild (LFW) dataset. FaceNet achieves a new record for accuracy at an astounding 99.63%. It uses its unique algorithm, plus an artificial neural network, and is incorporated into Google Photos to automatically tag pictures when a person is recognized.

FaceApp

In the summer of 2019, one app swept the nation and went viral -- FaceApp. From celebrities to NBA players, to even my family over Sunday dinner, everyone was using the app to upload a selfie and see how they look once they aged themselves into the future with the “old age” filter.

Using artificial intelligence and deep learning technology, FaceApp could do more than just age a photo, but also add lipstick and eyeshadow, change the hair color, and even add a beard or a mustache.

Face ID

In 2017, Apple launched Face ID on the iPhone X, allowing users to unlock their phones with a faceprint mapped by the phone’s front-facing camera. This software was designed by 3D modeling and is resistant to being spoofed by photos or masks as it captures and compares over 30,000 variables.

In addition to being able to unlock your phone, Face ID can also be used to make purchases with Apple Pay and the iTunes Store, App Store, and iBooks Store.

Benefits of facial recognition

There are more advanced benefits to facial recognition beyond tagging photos and unlocking our phones. Let’s explore how this innovative technology is benefiting society as a whole.

1. Combating crime

Law enforcement is one of the most obvious markets using facial recognition to detect and prevent crime. The same can be said for increased security at airports, as face match is used at border checks to compare passports with the holder’s face. Additionally, certain states allow law enforcement to run searches of driver’s license and ID photos., as this technology

2. Advancing healthcare

Thanks to deep learning and facial analysis, the healthcare industry can track a patient’s use of medication more accurately, support pain management procedures, and even detect genetic diseases with a higher success rate than ever before.

3. Improving retail sector

A newer develop in facial recognition called Know Your Customer (KYC) is combining facial recognition with marketing advances to improve the customer experience. This technology is placing cameras in retail stores to analyze the behavior of shoppers and is already being used by Saks Fifth Avenue and Amazon Go.

Markets Using Facial Recognition

 

In addition to these three markets, facial recognition can also enhance security on a personal level, as it is much harder to hack and than your password, which will decrease the chances of cyber crimes like identity theft. It can also be used to increase office security by means of access control, visitor and employee tracking, blacklisting certain individuals, and more.

More than just a face in the crowd

Your face says a lot about you. It can tell others when you’re sad, when you’re angry, or when you may not have gotten enough sleep. And, it’s also how you’re identified using advances in facial recognition. So no matter what kind of day you’re having, make sure to put your best face forward, you never know who’s watching.

Interested in learning more about the ins and outs of artificial intelligence? Check out this complete history of AI and artificial intelligence statistics.

Mara Calvello
Author

Mara Calvello

Mara is a Senior Content Marketing Specialist at G2. In her spare time, she's typically at the gym polishing off a run, reading a book from her overcrowded bookshelf, or right in the middle of a Netflix binge. Obsessions include the Chicago Cubs, Harry Potter, and all of the Italian food imaginable. (she/her/hers)