What if one day you were to wake up in the morning and you realize that you are unable to recognize people around you? What if all the faces around you looked equal? It would be terrible, wouldn’t it? Well, about 2% of the world’s population experience this, and they suffer from a rare condition known as “prosopagnosia”.

But what is prosopagnosia?

Prosopagnosia prevents the proper distinction of people’s faces, and can cause a serious problem in their life. The etymological origin of the word comes from the Greek “prosopon” (something like what is placed in front of the face and has subsequently resulted in the word “person”) and “agnosia” (or lack of knowledge).

Comparing this to the steps of automatic people’s facial recognition, we could say that someone with prosopagnosia is able to detect faces, but not to identify them. So he is not able to compare it against his database of known people. The diseased person will try to use other distinctive features of the person, perhaps a mole, a certain haircut, a tic, etc.

Yes, it can be prevented

In this regard, there is the question of why many Governments or Security Forces still suffer from prosopagnosia. In fact, if it were a disease attributable to public bodies that ensure our safety, the percentage of diseased would be far superior of that found in humans.

Today, facial recognition technologies are so advanced that they enable you to find someone in a crowd with frankly amazing success rates. Knowing this, it is difficult to understand why this technology is still not being commonly used at places such as airports, train stations, sport stadiums, border controls…

The world is moving in new paths where security plays an important role. Therefore, we should ask the leaders to be able to find a cure for this strange disease, which could limit our daily life significantly. Proposagnosia must be eradicated.

Written by: Javier Rodríguez Saeta

The increasing security concerns around the world, as well as the recent terrorist activities, are forcing governments to highly invest in video surveillance technologies to keep their countries safer. However, the applications of video surveillance are not restricted to homeland security alone, and include industries such as transportation, banking, retail and gaming as well.

Security is currently the main priority for everyone, and the use of video surveillance is not restricted to only protecting people.

Here are a number of industries that can benefit from the use of video surveillance in their environments.

Transportation

Security in public transportation is a major issue around the world. The daily flux of people who move around in different means of transport is immense. Airports or train stations are places where crime is habitually prevalent and systems for the identification of individuals can be hard to apply, as the volume of people is very high. In this sense, systems of facial recognition with video-surveillance make it possible to take advantage of the existing network of cameras to facilitate the search for specific individuals in crowds. These are usually systems operated by the police who work uninterruptedly, carrying out each minute multiple comparisons against a suspect database.

Government

The bodies and forces of security of the State are the guarantors for the protection of a country’s citizens. Their work involves using all the mechanisms within their reach that could help them in their daily endeavors. Amongst these mechanisms, technology has become a customary tool for Governments. So it is common to find biometric elements that help identify people in border control applications. Facial recognition is a highly recommendable technology for use in this type of surroundings, with potential applications in a wide variety of ambits.

Retail

The retail sector needs to resolve the problem of the frequent thefts that take place in shops. This type of crime is characterized by the fact that it is usually the same people who repeatedly commit these infringements. Consequently, having a system at their disposal that makes it possible to identify this type of subject in the most vulnerable places, ends up being fundamental to avoid frequent thefts. The existence of databases with the faces of recurring offenders can help to resolve this problem.

On the other hand, there is also a growing interest in identifying the typology of the clients of a certain business. Systems of facial marketing permit the analysis of visitors’ faces providing demographic data that makes it possible to establish the profiles of habitual clients.

Finance

The banking sector is especially open to adopt novel technologies capable of automating and accelerating processes for person identification. The aim is twofold. On the one hand, it is interesting to authenticate their customers, not only at the time of carrying out bank operations, but also the very moment they enter an office, using either whitelists or blacklists. On the other hand, it is useful to access the profile of the visitors and count the daily number of customers in an office, in order to optimize the resources and personnel of the workplace. In this sense, facial recognition is one of the least invasive and more generally accepted technologies.

Sports & Events

Sports stadiums are often subject to vandalism and as places where a large number of people congregate any incident can become a human tragedy.

Currently people who are prohibited entry to stadiums manage to flout this prohibition with impunity. Conventional security systems are not able to limit the access of specific individuals to stadiums due to the fact that entrance tickets are not generally nominal.

In this regard, facial recognition technology can realize a survey, in real time, of all the faces at a specific access point and send an alert if it detects the presence of any person whose entry to the enclosure is not authorized.

Gaming

Casinos and the gambling sector in general are interesting scenarios for the use of facial recognition technologies. The need, on the part of the security team of a casino to identify people is paramount. They have to be able to determine the people for whom access is not authorized, particularly in those countries where there is no national identity card.
In these surroundings, there is also a need to identify the presence of the best clients (VIPs) of a particular establishment. Facial recognition technology can be of great assistance in this sense, through the use of so-called whitelists.

Written by: Laura Blanc Pedregal

In this rapidly growing world we live in, technological innovation has been amust for most of the industry sectors. The changes are quite evident: we’ve gone from writing down our homework and hand it in to our teacher, to sharing it online in a common blog between our classmates. Or from doing mathematical calculations manually to just tapping on the numbers on a calculator and let it do its work. There is no doubt that technology only brought us a higher sense of comfort and so made our lives much easier.

Facial recognition software has been experiencing an amazing innovation progress, and its capabilities have broadened significantly. Facial recognition is evolving and getting smarter constantly because people are using it more, even if we don’t even realize about it.

Let’s have a look at our daily life. Social networks have introduced a facial recognition software that automatically recognizes people identity, and suggests to tag the person in the picture. Many apps are also using this software to detect faces and make modifications through some editing tools, or guess the age and gender of the subject detected.

“One of the reasons why face recognition is so popular is that face images exist of almost everybody”, said Kevin Bowyer, an expert on biometrics and chair of the department of computer science and engineering at the University of Notre Dame.

And if you think about it, the progress that has been made in facial detection and identification just in the last decade is impressive.

Accurate and Unique

Now, moving beyond the debate of security versus privacy, it is necessary to understand how facial recognition technology helps improve people and businesses wellness in many different levels.

Surveillance in general is now found in our daily basis. And facial recognition is used in many ways such as social media, commercial businesses, sports events, banking, law enforcement and transportation. According to NIST, today’s facial recognition algorithms are proven to be 10 times more accurate than those of 2002, and 100 times more accurate than those of 1995, so it’s a software that’s still experiencing a fascinating innovation.

Biometric recognition offers a high level of security for businesses and industries. Many countries are benefiting from the use of face-recognition in their services and events, and their reputation increases due to the safety that their citizens experience. Now, this technology enables us to identify foreign people that are willing to visit our country, enhance the probabilities of detecting intrusive and trouble-makers, and allowing/denying access in specific areas.

But just as many other technologies, it is not as easy as it may look. “Identification is a very messy process. It’s as messy for computers as it is for humans” said Kelly Gates, author of Our Biometric Future: Facial Recognition Technology.

“People look like each other, people look different over time… ​You can never establish certainties; you can only establish probabilities of matches.”

Additionally, the concept of face-recognition is intrinsically cool, and its advantages are obvious. How many science fiction films, cartoons and comic strips have pushed for the idea of biometric technology? We might soon be able to pay in stores just by scanning our facial features!

Did you know?

Facial recognition studies started in 1960’s, with Woody Bledsoe along with Helen Chan Wolf and Charles Bisson – pioneers of automated facial recognition – worked together using the computer to recognize human faces.

Until now, there have been many improvements in biometric technology, not only facial recognition but also fingerprint and iris identification. However, the key factor that has made face recognition a relevant tool for security is that it does not require having a direct contact with the subject. This is why many industries keep investing on research and improvements for face recognition technology, leading to the possibility of recognizing faces in high resolution images and cameras as well as new algorithms that are able to distinguish identical twins.

Written by: Laura Blanc Pedregal

The term facial recognition is used to describe the process in which a computer application verifies a person’s identity. The software is used to detect the location of a specific face in a particular photo or video, and it’s wise enough to ignore other surrounding objects such as buildings, animals, cars or trees.

Now, simply from a person’s face, it is possible to tell people’s gender, their approximate age, whether they use glasses or not, and even how they are feeling. So there is no doubt that a human face is a rich source of very valuable information.

Human beings are able to process faces very quickly. It only takes us less than one second to recognize someone and even to determine how they are feeling. In the case of the software, however, it takes a more complex but very accurate process.

In other words, this process starts by examining the picture or video, then it determines if there are any faces in that frame by distinguishing them from the background. This procedure is done despite poor illumination, camera distance or changes in the orientation of the face.

Difference between facial detection and facial recognition

You might be wondering… “But if the software detects a face, it is because it was recognized”. Well, that is the idea, more or less.

Unfortunately, the terms facial detection and facial recognition have been misused, especially by the media, who often have a hard time distinguishing the two processes. As mentioned above, the idea is that in order to have facial recognition, first of all there must be facial detection.

Facial detection is the process in which the software determines, through algorithms, whether there are human faces in a picture or video. It does not determine a person’s identity; it only tells whether there are faces in there. For that reason, face detection does not store any information or detail about the detected person, it’s completely anonymous. So if the software detects a face in a particular picture, and this same face is detected again later on, it will not recognize that face as being the same person, since it will just provide a detection of a human face in a certain picture or frame. However, it will be able to keep some demographic information, such as gender or age of the person, being useful for demographic statistics. In conclusion, face detection by itself does not recognize an individual.

Moreover, facial recognition identifies automatically. This means that the software makes a positive identification of a person’s face, in a photo or video, against an existing database of faces. This recognition is possible because the face has been previously enrolled into a database of subjects. In order for face recognition to provide a successful recognition, the face needs to be enrolled following some quality criteria, like frontality, illumination or face size (in pixels).

Next, the software will determine unique facial key points used to identify the specific person enrolled into the database. In the next place, the system will use these key points to compare them against the information from the new picture or video. And then, if the face has a high level of confidence it will mean that there is a ‘match’, so the concrete face will then have been ‘recognized’.

There are many details that are necessary to recognize a person’s identity or characteristics, details that are undetectable to the human eye. But now, thanks to the incredible new technology developments, we are able to build hi-tech software that’s even capable of recognizing multiple faces in changeable and crowded environments, such as airports, train stations, shopping malls, sport stadiums…

Just as Herta’s CEO, Javier Rodríguez says “the human eye is the most perfect machine that exists. Although a machine may have in memory millions of faces that human beings could not recognize”.

Do you have any idea about how you could use facial recognition? Get in touch with us!

Written by: Laura Blanc Pedregal

Traditionally, the semiconductor industry has been capable of increasing the clock speed of computer devices while doubling the number of transistors at each new generation. Unfortunately, due to power constraints, clock frequency growth stalled in the past decade and major microprocessor manufacturers switched their product portfolios to many-core architectures. Modern GPUs go even further and currently integrate hundreds of simple cores at a reasonable power budget. Due to this fact, software companies have been struggling to adapt and map traditional sequential algorithms that were conceived for serial execution to these new devices. This parallelization task is not as easy as one may think. Generally, humans tend to naturally think their actions in a sequential fashion. Are you capable of quickly envisioning hundreds of simultaneous actions (some of them even with interdependences) in parallel? Most of the best minds and programmers in the world aren’t. And this is reasonable. In our daily lives, we tend to be overwhelmed at work if we have to deal with nine or ten important things at the same time. But put simply, it seems that our brain is not designed to deal with multitasking. The more tasks we intend to do in parallel (for example, answering an email while taking a phone call), the more likely is that we cause an error due to insufficient attention. That’s the reason why writing optimized and scalable parallel code that targets devices such as GPUs is a long and tedious process. Writing code for these architectures is usually error prone and difficult to debug. It is not uncommon to spend months writing efficient parallel code for a particular kernel operation whose serialized version could be easily programmed and tested in a couple of days.

In this new era of parallel computing, if a company wants to release a software product that fully exploits the capabilities of the latest parallel hardware available in the market, surely it has to invest more money and resources than they were required in the past. We at Herta Security started to adopt parallelization since the very beginning in our products, and soon realized that biometric algorithms can greatly benefit from fine-grain parallelization and data-parallel vector computations. Multiples stages of the traditional biometric pipeline such as the feature extraction process are inherently parallel. However, the complexity of the memory access patterns of some features make strategies such as data reuse, caching and prefetching challenging. With the advent of GPU computing, the programmer has now to deal with millions of concurrent threads, synchronize them, and efficiently exploit the heterogeneous cache architecture of these devices in order to reduce latency as much as possible. Even though these tasks are time consuming from a research and development perspective, they enable us to deliver good quality products that scale nicely with the latest advances in hardware while providing an unbeatable user experience.