Did you find yourself surprised when you realized for the first time that Facebook recognizes all your friends and tags them automatically as soon as you upload their photo? Well, I was and it was that one instance when I figured out that the machines and technologies around are only getting smarter and will soon overtake the human-smartness if they were to compete. Face recognition system is one of those technology marvels where a machine can act almost as intelligently as that of a human, that is it can recognize a human from its face and distinguish them from the rest.
How Does Face Recognition Work?
In human beings, it is the temporal lobe of the brain which is responsible for recognition of faces. The neurons of the temporal lobe respond to certain features of the face and stores them eventually leading to face identification.
In machine learning system, the machines are often fed a huge bank of images which the system absorbs and stores. When a face is to be matched, it tries matching it with the stored images using face recognition algorithm. According to a new research by a group of researchers at MIT, the machines spontaneously and accurately identifies the image, and sometimes was capable of identifying a face even when it was rotated at an angle of about 45 degrees from the center, to left or right.
Face Recognition in Facebook: DeepFace
A deep learning facial recognition system in artificial intelligence called the “DeepFace” has been developed by a group of researchers in the Facebook which identifies human faces in a digital image very effectively. DeepFace in Facebook makes use of a nine-layered neural network with 120 million connection weight and is trained on four million connection images uploaded by the Facebook users. The system is said to be one of the smartest with 97 percent accuracy compared to that of FBI’s Next Generation Identification System which is 85 percent accurate. According to researcher Ben Goertzel, Chief Scientist of the robotics firm Hanson Robotics Facebook had “pretty convincingly solved face recognition” with this project. Though the technology has been termed “creepy” by a Huffington Post article owing to privacy breach concerns, it is one of the most efficient face recognition systems developed.
FaceNet: A Google Project
In 2015, a trio of Google researcher published a paper on face recognition in artificial intelligence dubbed as FaceNet. It claimed to use a highly accurate method for face recognition achieving a close to 100 percent accuracy on a face recognition dataset known as Labeled Faces in the Wild which included more than 13,000 images of faces from across the world. With 260 million image-dataset fed as training, FaceNet performed with over 86 percent accuracy. The system can give a name to a face and can even present collections of faces that looks most similar or the most distinct. This research points to a not so far future when face recognition will become extremely common in a wide range of activity ranging from criminal investigation and surveillance to business.
Uses of Face Recognition System
Fraud Detection for Passports and Visas
According to reports, experts using the automatic face-recognition software in Australian Passport office are 20 percent more efficient as compared to average people detecting fraud. An effective tool to detect fraud, face recognition is increasingly being used to identify documents such as driving license and immigration visas.
ATM and Banks
China started using the first face recognition technology in the ATMs. The new cash machine developed using this technology ensured increased security of the card user and worked by mapping facial data, matching it against the database. As a part of the biometric authentication, it used the data from facial features and iris recognition.
Identification of Criminals
An increasingly popular tool among the law enforcement agencies, face recognition technology has significantly contributed in the domain of investigation and crime detection. Several countries including the USA is building the facial recognition database, to improve the quality of the investigation. According to a report released by the Center for Privacy and Technology at Georgetown University law school, the law enforcement database in the U.S includes 117 million individuals.
Prevent Fraud Voters
Face detection was used in 2000 presidential election in Mexico to prevent duplicate voting. Several individuals had attempted to vote multiple times using different names. The duplicate votes were prevented to a great extent, thanks to the face recognition technology.
Face recognition system is being used by some organization to track the attendance of the employees. The system collects and records the facial fine points of the employees in the database. Once the process is done, the employee only needs to look at the camera and the attendance is automatically marked in the face recognition attendance system.
- Keep Track of the Members
Several churches across the world are using face recognition technology to keep a track of the church-goers. The places include India, Indonesia, and Portugal. The CCTV footages of the churchgoers are matched against a database of high-resolution images which a church has to compile on its own.
Threats and Concerns
According to several civil right groups and privacy campaigners, the face identification takes away the right of the people to remain anonymous. According to these people, the government agencies and private companies are unwilling to accept the fact that they should necessarily seek permission first before using data like face recognition as these will leave people identifiable wherever they go. Not just this, all the scattered bits of data left behind everywhere due to our digital presence can be put together to find out every minute detail of us as a person, which may include our taste, preference, friends, habits and movement. In Europe and Canada, the organizations will have to seek permission before using face recognition technology. In the United Kingdom, one must be informed when they are under surveillance and by whom. All these makes the face recognition technology scene a little complicated despite the benefits that it poses.
If you want to read more such interesting articles on artificial intelligence, its applications and how it is changing the world for us, stay tuned to acadgild.com