In the era of isolation, how can facial and fingerprint recognition “previous to failure”?

With only one month left until the end of 2020, domestic social order is recovering rapidly and getting back on track, but all fields still have to bear the irreversible impact of the epidemic and face the challenge of reconstruction.

As far as biometrics are concerned, fingerprint recognition was the most widely used before the epidemic, but during the epidemic it was regarded as an "unsafe" biometric method due to its contact-based action; before the epidemic, facial recognition was the most convenient, but now one needs to take off the mask first to complete this action, which is a bit cumbersome.

On the other hand, contactless biometric identification methods such as vein recognition have shown their advantages during the epidemic and seem to be gradually occupying a larger market.

Will biometric technology face a reshuffle amid the pandemic?

[[350442]]

Fingerprint and facial recognition are still the mainstream

In the current biometrics, the main identification methods include fingerprint recognition, face recognition, iris recognition, palm print recognition, voice recognition, vein recognition, etc. Based on different principles and the maturity of the industrial chain, fingerprint recognition and face recognition have occupied the mainstream position for a long time.

However, according to the latest report from ABI Research, due to the impact of the epidemic, smartphone shipments have declined, and contact-based recognition carries the risk of spreading the new coronavirus. It is expected that by the end of this year, global fingerprint recognition revenue will fall by 22% to US$6.6 billion.

Fingerprint recognition has gone through many iterations since its development. In 1998, Siemens launched the world's first prototype with fingerprint recognition technology. The sliding fingerprint recognition it adopted was developed until 2013. It was not until the release of the iPhone 5s that the first press-type fingerprint recognition entered the market, and fingerprint recognition was truly known to the public. Today's fingerprint recognition has long broken the limitations of the press-type and has developed in capacitive, optical and other aspects.

At the 2020 Biometric Technology and Application Forum, Liu Haolei, ToF Marketing Director of GigaDevice's Sensor Business Unit, said that fingerprint recognition has expanded from capacitive to optical and ultrasonic, and exists in their respective market segments based on the product's own characteristics and design requirements.

Liu Haolei believes that compared with capacitance and optics, the biggest feature of ultrasound is that it is not affected by the material. It can penetrate glass, metal, plastic and other materials, and is not restricted by dirty environments and wet fingers. Ultrasonic fingerprint recognition has broad prospects.

After smartphones were equipped with fingerprint recognition, face recognition entered the field of consumer electronics. It uses cameras to collect facial images or videos, and automatically detects or tracks faces in images to complete recognition. Face recognition has undergone a transformation from identification type to confirmation type to attention list type. With the improvement of algorithms and systems, it has become more widely used. The accuracy of face recognition technology for wearing masks, which has grown with the epidemic, is continuing to rise.

The security of facial recognition has always been a concern. According to the "Public Survey Report on Facial Recognition Application (2020)", 60% of respondents believe that facial recognition has a tendency to be abused, and 30% of respondents said that their privacy or property security has been affected by the leakage or abuse of facial information. Faced with a security risk, facial recognition is changing from 2D to 3D.

Compared to 2D which can only obtain two-dimensional images, 3D recognition can collect up to hundreds of thousands of information points, obtain depth information, and prevent fake identities. At present, a considerable number of mobile phones are equipped with ToF lenses to achieve 3D perception. It is worth noting that the iToF, which is more accurate and less expensive, is currently used for face recognition, while dToF is mainly suitable for longer distance measurement, such as 2.5 meters measurement by the rear camera.

At this year's Biometric Technology and Application Forum, Li Minghao, manager of field application engineers at ams Semiconductor, said in a dialogue with the media that single-point ToF is currently mainly used in mobile phones and has a lower cost. As the cost of array ToF decreases, its effect and application will be further expanded.

Although fingerprint recognition and facial recognition have inevitably been impacted by the epidemic, these two technologies are still developing and advancing. According to a recent data from Transparency Market, fingerprint recognition accounts for 58% of all biometrics and facial recognition accounts for 18%, and they are still the mainstream of biometrics.

Contactless biometrics is developing strongly

The other side of the epidemic is stimulating the economic growth of contactless biometrics, including vein recognition.

A new report from Future Market Insights predicts that contact biometrics will ride the wave of the COVID-19 pandemic, growing at a compound annual growth rate of 17.4% from 2020 to 2030, with the global market size increasing fivefold to $70 billion.

Vein recognition is a way of identifying identity by identifying specific wavelengths of light in flowing blood and analyzing vein images in the background. Vein recognition can be divided into finger veins, palm veins and eye veins, among which the eye vein has the lowest market share. Vein recognition itself is not a new technology, but its application lags far behind face recognition and fingerprint recognition.

At the end of September this year, Amazon launched the Amazon one hand-swipe payment device based on contactless vein recognition, which attracted great attention. Vein recognition is difficult to tamper with and steal, and is most widely used in the financial field, but generally requires large equipment to provide support.

[[350443]]

A representative of Nie Zedong's team from the Institute of Medical Engineering at the Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, stated at the 2020 Biometric Technology and Application Forum that finger vein recognition is similar to fingerprint recognition. Both require the person being identified to extend his or her hand into the image acquisition device to obtain the image. It is an active authentication. The difference is that it can be recognized without contact. With the help of the existing and widely established fingerprint recognition user habits, the promotion of vein recognition has huge advantages.

"However, current vein recognition products still face problems with imaging and accuracy. 3D rotation and finger offset can cause recognition problems, and as people age, it will also be affected," said a representative of Nie Zedong's team.

However, this does not hinder the growth of the vein recognition market. Relevant reports predict that by 2020, the market share of vein recognition will increase from 2% in 2015 to 8%, with a market size of approximately US$2 billion.

In addition to vein recognition, according to GIA's forecast, the global iris recognition market will have a compound annual growth rate of 18.8% from 2020 to 2027, and the market size will reach US$10.3 billion by 2027. The compound annual growth rate of voice biometrics will be 17%.

Multimodal fusion is the future trend

"In terms of ease of use, variability and security, different biometric features have their own advantages and disadvantages. Take fingerprints, veins, faces and irises for comparison. The accuracy of fingerprint and face recognition is much lower than that of veins and irises. We predict that multimodal biometric fusion will become more and more common in the future. For example, the handling of banking business has transitioned from the earliest authorized smart cards to fingerprints plus smart cards, and then continued to evolve into fingerprints plus facial recognition, or possibly fingerprints plus irises." said Liu Haolei.

Similar to the trend of sensor fusion, biometrics based on various sensor technologies is also moving towards multimodal fusion.

Perhaps, this is the real "reshaping" of biometrics during and even after the epidemic.

All unmarked images in this article are from GigaDevice

This article is reproduced from Leiphone.com. If you need to reprint it, please go to Leiphone.com official website to apply for authorization.