contador javascript Skip to content
Contact :

What is facial recognition ?: How it works and these are its implications Martin / CNET

Facial recognition is a flourishing field of technology that is both exciting and problematic. If you have ever unlocked your iPhone just by looking at it, or have you asked Facebook or Google to review an unclassified album and show you the photos of your children, then you have seen facial recognition in action.

Whether you like it or not, facial recognition (sometimes also called "face or face recognition") is ready to play an increasingly important role in your life. They can scan your face at airports or concerts, with or without your knowledge. You can start receiving personalized ads thanks to the cameras of the shopping centers. Facial recognition has a lot of potential. This technology could help the devices to smart homes They will get smarter, send you notifications based on who they are watching and give you more convenient access to friends and family.

But even in the best case, facial recognition raises questions about questions of Privacy. Experts have a range of concerns ranging from abuses in law enforcement, to systems with hidden racial prejudices, or that hackers can access your secure information.

But what is facial recognition, how does it work and where is it currently in use?, And what are the implications of this rapid expansion technology sector?

What is facial recognition?

Facial recognition is a form of biometric authentication that uses body measurements to verify your identity. Facial recognition is a subset of biometric data that identifies people by measuring the unique shape and structure of their faces. Different existing systems use different techniques, but fundamentally, facial recognition uses the same principles as other biometric authentication techniques, such as fingerprint scanners and voice recognition.

How does facial recognition work?

All facial recognition systems capture a two-dimensional or three-dimensional image of a person's face, and then compare the key information of that image with a database of known images. In the case of police forces, that database can be collected from police identification photographs. In the case of smart home cameras, the data is likely to come from images of people you have identified as family or friends through the camera application.

Woodrow "Woody" Bledsoe was the first to develop a software of facial recognition, for a company called Panoramic Research in the 1960s, using two-dimensional images, and with funds for research from an intimate intelligence agency.

Even now, most facial recognition systems rely on 2D images, either because the camera does not have the ability to capture depth information such as the length of your nose or the depth of your eye socket, or because the basis of Reference data consists of 2D images, such as police or passport photos.

2D facial recognition mainly uses reference points such as the nose, mouth and eyes to identify a face, and measures both the width and shape of the features, and the distance between them on the face. These measurements are then converted into a numerical code by means of a software of facial recognition, which is used to find matches. This code is known as "facial footprint" (faceprint).

This geometric system can present problems due to variations in the angle and illumination. For example, the image of a face captured from the front show a different distance between the nose and the eyes than that of a face turned to the side. This problem can be partially mitigated by moving the 2D image to a 3D model and undoing the rotation.

Apple uses a 3D facial recognition system called Face ID. It is good, but not perfect.

Morgan Little / CNET

Adding a third dimension

He software 3D facial recognition is not easily fooled by angles and light, and is not based on the average size of a head to identify a facial footprint. With cameras that detect depth, the facial footprint can include the contours and the curve of the face, as well as the depth of the eyes and the distances from reference points such as the tip of your nose.

Most cameras measure this depth by projecting invisible spectra of light on your face and using sensors that capture the distance of several points of this light in relation to the camera. Although these 3D sensors can capture much more detail than 2D, the basis of the technology remains the same: convert the various shapes, distances and depths of a face into a numerical code and match that code with a database.

If that database is made up of 2D images, the software You must first convert the 3D facial fingerprint to a 2D to find a match.