facial recognition

The 3D optical sensing market is once again surging – and it’s all thanks to Apple. What will we see in the next wave of end products enhanced by this technology, how will other market segments approach – and eventually use – 3D optical sensing, and which suppliers stand to gain the most from this very vital technology?Although 3D sensing, facial recognition and optical authentication systems have become only recently hot topics in the consumer electronics market, these mechanisms first made their appearance nearly a decade ago in November 2010. Following that debut, Microsoft soon launched the Kinect system in its Xbox 360 gaming console, marking a milestone as significant as Nintendo’s launch of its Nintendo Wii remote controller in 2010, which catapulted MEMS motion sensors into the high-volume consumer market.The Kinect system used a triangulation-based camera that Israeli developer PrimeSense Ltd. created and then licensed to Microsoft; Apple liked the technology so much that it acquired PrimeSense in 2013. The first version of Kinect applied the Structured Light (SL) method, a depth-sensing principle featuring an infrared (IR) laser projecting dots onto the scene, with a monochrome CMOS sensor measuring the differences in the acquired pattern. The second version of Kinect used the Time-of-Flight (ToF) principle.Kinect for Xbox360 was not only a successful consumer product; it also sparked a new market, thanks to the relatively low cost of the 3D sensing solution. By using the same hardware for Xbox 360 as in its first version of Kinect, Microsoft allowed developers to design their pet projects in the Kinect environment. Adding hand gestures controls to a PC, creating a user-controlled virtual dynamic light (see Kimchi and Chips’ demo), and developing an inexpensive hologram generator (see “Princess Leia” video from the MIT Media Lab) are just a few examples of ecosystem developers and DIYers applying their creativity to Kinect.Apple Goes 3D with Face ID3D optical sensing has expanded from gaming consoles to the smartphone. In 2017 Apple presented its Face ID camera system for the iPhone X, which they launched to celebrate the 10-year anniversary of the iPhone. Face ID is the result of a longer term strategy for Apple, the byproduct of several company acquisitions to expand know-how in 3D sensing and augmented reality (AR)/virtual reality (VR). Between 2015 and 2018, Apple acquired the camera-module maker LinX (2015), the AR startup Vrvana and the imaging sensor firm InVisage Tech (both in 2017), and AR glasses’ designer Akonia Holographics (2018).For a company that has always innovated on its own terms, Apple’s idiosyncratic approach called for deployment of the Structured Light method combined with a ToF device. The result is an amalgamation that utilizes the best features of the two mechanisms, even if the combination is one that is expensive. Apple’s addition of a near-infrared illuminator to its ToF device enhances the system’s effectiveness under most light conditions while also improving the reliability of Face ID; the overall outcome is a more satisfying user experience. The ToF component, which STMicrolectronics supplies, makes use of so-called single-photon avalanche diode (SPAD) receivers that can work with any target material and color, although a higher target illumination is required to obtain good accuracy.The other core components of the Face ID system are the Vertical Cavity Surface Emitting Laser (VCSEL, from Lumentum) and a dot projector (from ams/Heptagon), assembled together in an optical package. Apple’s expensive but reliable approach explains the company’s inclusion of the Face ID system in its latest smartphone and tablet offerings – across the iPhone Xs, Xs Pro and Xr as well as in the latest iPad Pro models. Apple’s Face ID uses facial recognition for authentication on a range of iPhone and iPad Pro models. Image courtesy of Apple. Chinese Phone Makers Get into the GameMeanwhile, other mobile handset manufacturers are rumored to be working on Face ID-like systems or have already presented similar solutions, albeit through a variety of approaches. Some have chosen to use standard ToF devices while others have adopted an SL tactic. In many of these designs, which happen to target Android systems, OEMs generally include a fingerprint sensor as a fallback biometric option to their own nascent 3D facial recognition systems. The fingerprint sensor operates in either standalone mode or integrates into the display.Chinese handset maker Oppo, for instance, uses the SL method on its Find X model with algorithms coming from Megvii. Oppo claims its equivalent of Apple Face ID is faster. I have heard that Vivo has been working on a ToF camera since mid-2018, which it claims provides greater accuracy and security in end-applications such as secure payments and unlocking the phone.Chinese technology giant Huawei’s first 3D facial sensor appeared in its Mate 20 Pro flagship mobile phone. Aside from providing facial biometrics, the front-facing 3D sensor doubles as a 3D scanner, enabling users to digitize live objects that they can then manipulate in 3D AR applications. While still a novelty, the application highlights the use of 3D light sensors beyond that of biometrics. Xiaomi’s Mi Explorer Edition smartphone features a complex SL 3D module to enable 3D facial scanning although it looks like a clone of the Apple solution.Overall, the importance of facial recognition is no longer a matter of dispute, given that Apple’s rivals are now developing counterpart offerings of their own. Leaked code from the next revision of the Android operating system (revision Q), now under development by Google, has confirmed as much. Big and Getting BiggerIHS Markit forecasts that global revenue for ToF sensors in the 3D optical sensing market will surpass $500 million in 2019, up from $370 million last year. We also predict that the ToF market will grow in the coming years, spurred by combo solutions integrated with other light sensors in the same package. This will lead to a cheaper bill of materials (BOM) compared to the BOM for the SL method.At the same time, IHS Markit forecasts that the total market potential for light sensors will be worth much more, reaching $1.5 billion by year 2022. That’s because after a solid start with gaming consoles, 3D sensing has matured and consolidated in the massive smartphone arena.A segment of 3D Sensing’s future growth will come from other use cases and applications that are emerging outside consumer electronics and mobile. These include people-counting and -tracking in consumer and industrial applications, landing-aid and obstacle-avoidance functions in drones, and car-trunk (boot) opening with foot gestures, as well as gesture recognition and passenger detection in automotive. IHS Markit predicts steady growth for ToF and other light sensors. All told, the ToF approach appears to have a greater chance than the SL method in gaining a larger market share, leading to a cheaper and smaller BOM along with reduced integration costs in system assembly and calibration.Sometime this year, Apple and other handset OEMs may include a ToF-based 3D camera on the back of the iPhone to support more immersive gaming experiences and new AR/VR applications. This will further boost the 3D sensing market.To be sure, other mature technologies are available as valid alternatives to optical 3D sensing, including ultrasonic, mmWave and radar. These alternative technologies may gain part of the total market now commanded by 3D sensing, in use cases such as obstacle-avoidance or in-cabin presence detection.To learn about 3D Optical Sensing and Light Sensors from IHS Markit, go to: https://technology.ihs.com/606483/light-sensors-for-consumer-mobile-report-2018Manuel Tagliavini, a principal research analyst at IHS Markit, covers MEMS and sensors technology.Manuel Tagliavini joined IHS Markit in 2017. His key areas of focus are MEMS and sensors for mobile and consumer technologies. He is responsible for the tracking of sensors in handsets, tablets, laptops, and sports and fitness products.Prior to IHS Markit, he spent over 10 years with STMicroelectronics, working in various roles including product engineering, program management, and marketing and business development in the company's MEMS division.Tagliavini earned an Executive Master of Business Administration at SDA Bocconi School of Management and a Master of Science in Electronic Engineering from the University of Parma, both in Italy.Stay tuned with the technological advances and market trends in the MEMS Sensors ecosystem. Join MEMS Sensors Industry Group (MSIG), the SEMI technology community that connects the MEMS and sensors supply network in established and emerging markets, allowing members to grow and prosper.

2017 was a good year for the MEMS and sensors business, and that upward trend should continue. We forecast extended strong growth for the sensors and actuators market, reaching more than $100 billion in 2023 for a total of 185 billion units. Optical sensors, especially CMOS image sensors, will have the lion’s share with almost 40 percent of market value. MEMS will also play an important role in that growth: During 2018–2023, the MEMS market will experience 17.5 percent growth in value and 26.7 percent growth in units, with the consumer market accounting for more than 50 percent(1) share overall. Evolution of SensorsSensors were first developed and used for physical sensing: shock, pressure, then acceleration and rotation. Greater investment in R D spurred MEMS’ expansion from physical sensing to light management (e.g., micromirrors) and then to uncooled infrared sensing (e.g., microbolometers). From sensing light to sensing sound, MEMS microphones formed the next wave of MEMS development. MEMS and sensors are entering a new and exciting phase of evolution as they transcend human perception, progressing toward ultrasonic, infrared and hyperspectral sensing.Sensors can help us to compensate when our physical or emotional sensing is limited in some way. Higher-performance MEMS microphones are already helping the hearing-impaired. Researchers at Arizona State University are among those developing cochlear implants — featuring piezoelectric MEMS sensors — which may one day restore hearing to those with significant hearing loss. The visually impaired may take heart in knowing that researchers at Stanford University are collaborating on silicon retinal implants. Pixium Vision began clinical trials in humans in 2017 with its silicon retinal implants.It’s not science fiction to think that we will use future generations of sensors for emotion/empathy sensing. Augmenting our reality, such sensing could have many uses, perhaps even aiding the ability of people on the autism spectrum to more easily interpret the emotions of others.Through my years in the MEMS industry, I have identified three distinct eras in MEMS’ evolution: The “detection era” in the very first years, when we used simple sensors to detect a shock. The “measuring era” when sensors could not only sense and detect but also measure (e.g., a rotation). The “global-perception awareness era” when we increasingly use sensors to map the environment. We conduct 3D imaging with Lidar for autonomous vehicles. We monitor air quality using environmental sensors. We recognize gestures using accelerometers and/or ultrasonics. We implement biometry with fingerprint and facial recognition sensors. This is possible thanks to sensor fusion of multiple parameters, together with artificial intelligence. Numerous technological breakthroughs are responsible for this steady stream of advancements: new sensor design, new processes and materials, new integration approaches, new packaging, sensor fusion, and new detection principles.Global Awareness SensingThe era of global awareness sensing is upon us. We can either view global awareness as an extension of human sensing capabilities (e.g., adding infrared imaging to visible) or as beyond-human sensing capabilities (e.g., machines with superior environmental perception, such as Lidar in a robotic vehicle). Think about Professor X in Marvel’s universe, and you can imagine how human perception could evolve in the future! Some companies envisioned global awareness from the start. Movea (now part of TDK InvenSense), for example, began their development with inertial MEMS. Others implemented global awareness by combining optical sensors such as Lidar and night-vision sensors for robotic cars. A third contingent grouped environmental sensors (gas, particle, pressure, temperature) to check air quality. The newest entrant in this group, the particle sensor, could play an especially important role in air-quality sensing, particularly in wearable devices.Driven by increasing societal concern over mounting evidence of global air-quality deterioration, air pollution has become a major topic in our society. Studies show that there is no safe level of particulates. Instead, for every increase in concentration of PM10 or PM2.5 inhalable particles in the air, the lung cancer rate is rising proportionately. Combining a particle sensor with a mapping application in a wearable could allow us to identify the locations of the most polluted urban zones.The Need for Artificial Intelligence To realize global awareness, we also need artificial intelligence (AI), but first, we have challenges to solve. Activity tracking, for example, requires accurate live classification of AI data. Relegating all AI processing to a main processor, however, would consume significant CPU resources, reducing available processing power. Likewise, storing all AI data on the device would push up storage costs. To marry AI with MEMS, we must do the following: Decouple feature processing from the execution of the classification engine to a more powerful external processor. Reduce storage and processing demands by deploying only the features required for accurate activity recognition. Install low-power MEMS sensors that can incorporate data from multiple sensors (sensor fusion) and enable pre-processing for always-on execution. Retrain the model with system-supported data that can accurately identify the user’s activities. There are two ways to add AI and software in mobile and automotive applications. The first is a centralized approach, where sensor data is processed in the auxiliary power unit (APU) that contains the software. The second is a decentralized approach, where the sensor chip is localized in the same package, close to the software and the AI (in the DSP for a CMOS image sensor, for example). Whatever the approach, MEMS and sensors manufacturers need to understand AI, although they are unlikely to gain much value at the sensor-chip level.Heading to an Augmented WorldWe have achieved massive progress in sensor development over the years and are now reaching the point when sensors can mimic or augment most of our perception: vision, hearing, touch, smell and even emotion/empathy as well as some aesthetic senses. We should realize that humans are not the only ones to benefit from these developments. Enhanced perception will also allow robots to help us in our daily lives (through smart transportation, better medical care, contextually aware environments and more). We need to couple smart sensors’ development with AI to further enhance our experiences with the people, places and things in our lives.About the authorWith almost 20 years’ experience in MEMS, sensors and photonics applications, markets, and technology analyses, Dr. Eric Mounier provides in-depth industry insight into current and future trends. As a Principal Analyst, Technology Markets, MEMS Photonics, in the Photonics, Sensing Display Division, he contributes daily to the development of MEMS and photonics activities at Yole Développement (Yole). He is involved with a large collection of market and technology reports, as well as multiple custom consulting projects: business strategy, identification of investment or acquisition targets, due diligence (buy/sell side), market and technology analyses, cost modeling, and technology scouting, etc.Previously, Mounier held R D and marketing positions at CEA Leti (France). He has spoken in numerous international conferences and has authored or co-authored more than 100 papers. Mounier has a Semiconductor Engineering Degree and a PhD in Optoelectronics from the National Polytechnic Institute of Grenoble (France).Mounier is a featured speaker at SEMI-MSIG European MEMS Sensors Summit, September 20, 2018 in Grenoble, France. (1) Source: Status of the MEMS Industry report, Yole Développement, 2018