Facial recognition and the uses of this technology
Facial recognition is a category of biometric software that maps an individual's facial features mathematically and stores the data as a face print. The software uses deep learning algorithms to compare a live capture or digital image to the stored face print in order to verify an individual's identity.
How it works
The software identifies 80 nodal points on a human face. In this context, nodal points are endpoints used to measure variables of a person's face, such as the length or width of the nose, the depth of the eye sockets and the shape of the cheekbones. The system works by capturing data for nodal points on a digital image of an individual's face and storing the resulting data as a face print. The face print is then used as a basis for comparison with data captured from faces in an image or video.
Even though the facial recognition system only uses 80 nodal points, it can quickly and accurately identify target individuals when the conditions are favorable.
High-quality cameras in mobile devices have made facial recognition a viable option for authentication as well as identification. Apple's iPhone X and Xs, for example, include Face ID technology that lets users unlock their phones with a faceprint mapped by the phone's camera. The phone's software, which is designed with 3-D modeling to resist being spoofed by photos or masks, captures and compares over 30,000 variables. Face ID can be used to authenticate purchases with Apple Pay and in the iTunes Store, App Store and iBooks Store. Smart advertisements in airports are now able to identify the gender, ethnicity and approximate age of a passersby and target the advertisement to the person's demographic.
Facebook uses facial recognition software to tag individuals in photographs. Each time an individual is tagged in a photograph, the software stores mapping information about that person's facial characteristics and can later identify people in new photos. .
Other examples of facial recognition include Amazon, MasterCard and Alibaba, who have rolled out facial recognition payment methods commonly referred to as selfie pay. Developers can use Amazon Rekognition, an image analysis service that's part of the Amazon AI suite.
* Facial recognition can be used for a multitude of applications, from security to advertisements. Some example use cases include:
* Mobile phone manufacturers, such as Apple, for consumer security.
* Government at airports, to identify individuals who may overstay their visas.
* Law enforcement through collecting mugshots to compare against databases from local, state, and federal resources.
* Business security, as businesses can use facial recognition for entry to their buildings.
* Marketing, where marketers can use facial recognition to determine age, gender and ethnicity to target specific audiences.
The use of facial recognition comes with it a host of potential benefits, including:
* No need for physical contact with a device for authentication thus no errors associated with them such as improper scan due to dirt on fingers. Improved level of security.
* Requires less processing compared to other biometric authentication techniques.
* Easy to integrate with existing security features.
* Accuracy of readings has improved over time.
* Can be used to help automate authentication.
* Security and privacy concerns.
Facial recognition systems are currently being studied or deployed for airport security in developed nations. Data from a facial recognition system may be captured and stored, and an individual may not even know. The information could then be accessed by a hacker, and an individual's information spread without ever knowing it. This data could be used by Government agencies or advertisers to track individuals as well. Even worse, a false positive may implicate an individual for a crime they are not guilty of.
How this can change Bangladesh scenario
As the demand for emerging technology is growing, facial recognition appears to be the fastest growing markets in technology. This is the perfect opportunity for Bangladeshi entrepreneurs to capture a portion of the market share, potentially acting as a force that both enhances the lives of our people and boosts the growth of our economy through the creation of jobs.
In the RMG industry today, one of the biggest obstacles is the presence of ghost workers. Due to the immense number of employees in each unit, it can be difficult to efficiently supervise each individual employee. This results in miscalculations of attendance, working hours, and efficiency, that can pile up to huge sums in losses. If each employee could be identified within the premise, their work hours could be accurately monitored, the overall work environment will be more secure, and valuable time will be saved.
Hotels and Hospitality is an industry where security and customer service are among the fundamental pre-requisites for its success. Using facial recognition, a hotel can identify a customer and determine their preferences, predict the likelihood of criminal behaviour, provide a more personalized and faster service, and improve the security of their payments through face authorization.
Schools in Bangladesh are a sector that could benefit from the implementation of Facial Recognition. By simply using their existing photo ID database, schools can automate their attendance systems. Students, Teachers, Staff and all affiliates of the school can be automatically checked in when they enter or exit the premise, making it easier to count attendance, enhance the safety of everyone.
With an average literacy rate of 93.3% of both men and women between the ages of 15-24 (UNESCO, 2018), Bangladesh has seen substantial growth in education and skilled citizens. When that is paired with our recent focus on the IT sector, the market for Artificial Intelligence gives us an opportunity to create millions of jobs. This will be a major contribution to the expansion of the middle class, creating opportunities for the next generation, and establishing a society that can grow as one.
The writer is Syed Tanzil Ahmed,
Chief Strategy Officer (CSO) at gaze.technology