Facial recognition is now a common element in mobile designs. Here’s a look at information related to facial recognition from across the industry.
ams launches a sensor for facial recognition from behind the device’s OLED screens
Last week, AMS released a new color (RGB light) and IR proximity sensor, the TCS3701. One of the notable factors of this sensor IC is that it enables mobile devices to process facial recognition from behind OLED screens. This allows for more design options, as engineers can have more flexibility as to where they could place these sensors on a device. It also means that a smartphone screen could effectively become a suite of sensors.
According to an ams press release, “Despite the restriction of operating behind an emissive OLED screen, the TCS3701 detects the addition of ambient light passing through the screen to the light emitted by the screen pixels located just above the sensor “. The company credits a non-predictive asynchronous algorithm with the device’s ability to perform ambient light, regardless of screen brightness and in a range of ambient light levels from weak to bright.
Schematic for TCS3701. Image of ams
According to Reuters, ams also supplies the optical sensors for 3D facial recognition for the iPhone, although ams does not publicly claim Apple as an official customer. This may suggest that such technology could end up in future iPhones.
This is just one avenue through which AMS works with facial recognition. In the first week of January, ams announced a new partnership with Face ++, a Chinese open AI platform that allows various forms of environmental recognition, including facial recognition, to be integrated into designs more quickly through an API. (Application Programming Interface) and SDK (Software Development Kit).
The TCS3701 joins the ams suite of 3D sensing products. There is an evaluation board for the IC, although a datasheet for the device itself is not yet publicly available.
- 2.0mm x 2.5mm x 0.5mm OQFN Package
- 1024x dynamic range
- 1.7 – 2.0 V supply voltage
- 1.8V I²C bus
- Recommended operating distance <50 cm
Omron Human Vision Components B5T-007001 (HVC-P2)
By changing gears to modules, Omron’s HVC-P2 provides the components for reconnaissance systems. First introduced in 2016, it consists of a small camera and circuit board that has advanced recognition capabilities. Models are offered with cameras for long distance or wide angle views. The component can be installed via USB (microUSB type B) or UART connections and includes ten different image detection functions.
You can, for example, detect and recognize faces, estimate age, gender, expression, and determine what users are looking at.
Image detection functions included are:
- Human body detection
- Hand detection
- Face detection
- Face direction estimation
- Age estimation
- Gender estimation
- Flicker estimation
- Expression estimation
- Facial recognition *
- Gaze estimation
* For facial recognition, registered users are identified while unregistered users are logged.
Image Sensor with Image Capability B5T-007001 White Paper
This sensor is currently configured for marketing applications; can be used to determine user engagement with an ad or vending machine. The variety of functions provided, however, used alone or together, make it suitable for many applications.
In marketing studies, estimates of expression can provide more useful feedback than subjects answering survey questions.
In energy applications, sensing the human body provides more efficient systems. Lighting and temperature can be controlled to provide comfortable environments when needed and save energy when no one is around. If you are not using a dining room or gym, for example, the systems can be turned off. When used, the systems turn on and as more people gather, they can be automatically adjusted to maintain a comfortable environment.
Engineers could certainly apply the technology to other fields. For example, the device can be installed in a car to adjust the driver’s seat and mirror for different drivers, recognized before entering the vehicle. Alternatively, it could be used in industrial settings and manufacturing plants to measure worker attention and alertness, perhaps triggering an alarm before a machine operator falls asleep, or notifying a supervisor that the operator of the machine falls asleep. the crane is playing on a smartphone.
In recent years, the HVC-P2 has found use in monitoring digital signage, as well as monitoring shopping districts in China (site in Chinese).
Neurotechnology SentiVeillance 7.0 Face Verification SDK
Also at the beginning of the year a new software development kit for facial recognition from the Lithuanian company Neurotechnology was announced.
One of the main challenges of the widespread use of facial recognition technology is the development of reliable algorithms to analyze large data sets. Neurotechnology’s SentiVeillance platform uses a biometric facial identification algorithm that they claim enables real-time analysis and creation of watch lists. Imagine, for example, a watch list created to assess safety in an industrial facility.
The algorithm reportedly allows individual faces to be tracked over a camera’s field of view, even as they pass behind objects. According to a press release, the company also claims that the algorithm “can perform a gender classification, assess a person’s age, identify facial expressions (eg, smile, open mouth, closed eyes)” and even identify if there are other factors, such as glasses. or facial hair.
As sensor technologies become more advanced in 2019, it is important that software follow suit to enable better data processing and ultimately better hardware functionality.
What are your predictions for the facial recognition industry in 2019? Share your thoughts in the comments below.
Featured image used courtesy of ams.