The development of science and technology over the past several decades has led to the creation of various innovations including smart phones and other devices including our laptops and smart watches we use daily.
These devices have been designed with security features meant to protect your personal information. They include pins, passwords, patterns, fingerprint sensors and facial recognition.
For the purpose of this article, we will focus on various elements of Facial Recognition Technology.
What is Facial Recognition?
Facial Recognition Technology refers to software that is embedded onto computer programs and devices that scan and analyze images of human faces for the purpose of identifying them and granting them the access they seek.
History of Facial Recognition Technology.
After all the security measures put in place for devices, three different people rose up on a certain day and decided that there has to be an addition to the list of the technology we already have. They are Charles Bisson, Woody Bledsoe and Helen Chan Wolf. In 1964 and 1965(1), the trio worked together on using the computer to scan and recognize human faces.
- Funding for the project came from an unnamed intelligence agency that did not want to be in the public eye.
- Led by Bledsoe, the project involved the manual marking of important parts of the face such as the eyes and mouth. Then, these parts were mathematically rotated by the computer to compensate for pose variation.
- One problem arose in the process because the trio did not have a very large database of images and only one photograph, they became faced with the issue of selecting a small set of records so one of the image records matched the photograph from the database.
- In 1966, Bledsoe described the problem in part by stating, “This recognition problem(2) is made difficult by the great variability in head rotation and tilt, lighting intensity and angle, facial expression, aging, etc. Some other attempts at face recognition by machine have allowed for little or no variability in these quantities. Yet the method of correlation (or pattern matching) of unprocessed optical data, which is often used by some researchers, is certain to fail in cases where the variability is great. In particular, the correlation is very low between two pictures of the same person with two different head rotations.”
- The project was nicknamed “Man Machine”(3). Bledsoe left the project in 1966 and the work was continued at the Stanford Research Institute, led by Peter Hart.
- In 1997, a system developed by Christoph von der Malsburg alongside his graduate students beat all of the other systems which has been developed by MIT and the University of Maryland. The Bochum system was solely developed through funding by the United States Army Research Laboratory.
- By 2006, there was a Face Recognition Grand Challenge (FRGC) where the systems algorithm technology was tested. High-resolution face pictures, 3-D face scans, and iris images were tested in this challenge. The results showed clearly that the new algorithms are 10 times more accurate than the face recognition algorithms of 2002 and 100 times more accurate than those of 1995.
How does Facial Recognition work?
Facial recognition has been designed to use artificial intelligence (AI) to compare facial images and determine whether there is a match. It has the ability to determine whether two facial images are of the same person, and whether a facial image matches any of the facial images contained in a particular database. These comparisons are known as 1:1 and 1:N matching respectively.
(Also Read: Future of Face Recognition Technology)
What is Facial Recognition used for?
As stated earlier, it is used to analyze images of human faces for the purpose of running them through a database to see if their faces match the faces in the database.
Facial Recognition Applications.
Here are 5 top facial recognition applications listed below:-
- Face DNA Test
If you are into science and tech, and you have not tried out these applications, you are missing a lot. Kindly look them up on Google for more information.
Benefits of Facial Recognition Technology.
Now, let’s take a look at some of the advantages of FRT.
Face recognition can make advertising more fun by making educated guesses at people’s age and gender. Some companies like Tesco are already planning on installing screens at gas stations with face recognition built in. It will only take little time before face-recognition becomes an omni-present advertising technology.
Locate Missing Persons
Facial recognition technology can be used to find missing children and victims of human trafficking. As long as the missing individuals are added to a database, law enforcement can become alerted as soon as they are recognized by face recognition whether at an airport, retail store or other public space. For instance, 3000 missing children were discovered in just four days using face recognition in India!
Protection of Law Enforcement
Mobile facial recognition applications such as FaceFirst, are already helping police officers by helping them instantly identify individuals in the field from a safe distance. This is achieved by giving them contextual data that tells them who they are dealing with and whether they need to proceed with caution. For example, if a police officer pulls over a wanted murderer at a routine traffic stop, the officer would instantly know that the suspect may be armed and dangerous and could call for back up.
For the Identification of People on Social Media Platforms
Facebook uses facial recognition technology to automatically recognize when Facebook members appear in photos. This has made it easy for people to find photos they are in and can suggest when particular people should be tagged in photos.
Isn’t this surprisingly amazing? Facial recognition can be used to diagnose diseases that cause detectable changes in appearance. For example, the National Human Genome Institute Research Institute, used face recognition to detect a rare disease called DiGeorge syndrome where there is a portion of the 22nd chromosome missing. Facial recognition has helped diagnose the disease in 96% of cases. As algorithms become more sophisticated, face recognition will become an invaluable diagnostic tool for all sorts of conditions.
Protect learning institutions from Threats
Facial recognition surveillance systems can instantly identify when expelled students, dangerous parents, drug dealers or other people that pose a threat to school safety enter school grounds. By alerting school security ,facial recognition can reduce the risk of violent acts.
Tracking of School Attendance
In addition to making our schools safer, facial recognition technology has the potential to track students’ attendance. Traditionally, attendance sheets allow students to sign another student, who is ditching class, in. China is already using face recognition to ensure students are not skipping class. Tablets are used to scan students’ faces and match their photos against a database to validate their identities.
Facilitation of Secure Transactions
In China, we have heard of financial service company called Ant Financial that enables customers to pay for meals by scanning their faces. Customers can place orders through a digital menu, and then use face scan as a payment option. After they have provided their telephone number , they can then purchase their meal.
To recognize Drivers
More car companies especially in Nigeria are experimenting with ways to use face recognition. A use of face recognition for automobiles is using a face to replace a key as a means of starting a car. Facial recognition technology can also be used to change radio stations and seat preferences based on who is driving the car. Facial recognition tech can even make drivers safer by recognizing and alerting drivers if they are drifting off or not focusing on the road.
Disadvantages of Facial Recognition
Variations in compared images
When variations occur in the position of the head, lighting conditions, and facial expressions in the two images that you want to compare, it can result in low accuracy and this is applicable to make-up, glasses, hats, and anything that partially obscures the face. Fortunately, there are a few ways to deal with these challenges such as the use of a large and diverse training set. Also, deep learning techniques are making it easier to correct for these variations.
Its accuracy is less than 100%
No facial recognition algorithm is 100% accurate even with the most sophisticated software, there is still a chance that an authorized person will be denied access in an access control scenario or vice versa. In these situations, human intervention will still be required. But, with accuracy rates improving and with the technology achieving 98% accuracy and higher, it is clear that this technology is useful in all but the highest-risk scenarios.
One of the biggest concerns that surrounds the use of facial recognition technology is privacy. This is a strong concern, and there are various measures that you can take to reduce the privacy risks when implementing facial recognition technology. They include: storing only faceprints/face embeddings and not the regular facial images; that is if your use case allows for this, storing and processing data locally, so that you have total control over the data and so that third parties do not have access and purging of data regularly.
In many cases, there are certain concerns that facial recognition software can be fooled by masks or copies of photos presented to the camera. To avoid this, many facial recognition programs incorporate liveness detection features ensuring that the submitted video is of a live person, and that it is captured in real time.
(Also Read: 5 Pros and Cons of Face Recognition Technology)
Frequently Asked Questions about Facial Recognition Technology
Q. Can facial recognition be fooled?
A. The facial recognition technology can be fooled. For instance, on Google’s new Pixel 4,facial recognition technology can be fooled by a twin or unlocked by someone else who looks a lot like you while you’re asleep.
Q. Is facial recognition safe?
A. It is not relatively more secure than Touch ID, as it is still very possible for someone to break into your phone if they really want to. Although photocopies and pictures will not fool it, it is not out of the question for an identical twin or sibling to unlock your phone using Face ID. In the highly unlikely event that you are compromised, changing your face on your device would be a bit more challenging than changing your password!
Facial Recognition Technology is very good for the purpose of our day to day security. However, as clearly shown above, it is not perfect or error free. As most tools and technologies do, facial recognition comes with both advantages and disadvantages. For all purposes that are good, the advantages far outweigh the disadvantages. Download some of the applications listed above and give your device a little bit of security.