Facial expression reading based on MLP classification from 3D depth maps and 2D images obtained by NIR-LFC
Machine-learned, light-field camera reads facial expressions from high-contrast illumination invariant 3D facial images
A joint research team led by Professors Ki-Hun Jeong and Doheon Lee from the KAIST Department of Bio and Brain Engineering reported the development of a technique for facial expression detection by merging near-infrared light-field camera techniques with artificial intelligence (AI) technology.
Unlike a conventional camera, the light-field camera contains micro-lens arrays in front of the image sensor, which makes the camera small enough to fit into a smart phone, while allowing it to acquire the spatial and directional information of the light with a single shot. The technique has received attention as it can reconstruct images in a variety of ways including multi-views, refocusing, and 3D image acquisition, giving rise to many potential applications.
However, the optical crosstalk between shadows caused by external light sources in the environment and the micro-lens has limited existing light-field cameras from being able to provide accurate image contrast and 3D reconstruction.
The joint research team applied a vertical-cavity surface-emitting laser (VCSEL) in the near-IR range to stabilize the accuracy of 3D image reconstruction that previously depended on environmental light. When an external light source is shone on a face at 0-, 30-, and 60-degree angles, the light field camera reduces 54% of image reconstruction errors. Additionally, by inserting a light-absorbing layer for visible and near-IR wavelengths between the micro-lens arrays, the team could minimize optical crosstalk while increasing the image contrast by 2.1 times.
Through this technique, the team could overcome the limitations of existing light-field cameras and was able to develop their NIR-based light-field camera (NIR-LFC), optimized for the 3D image reconstruction of facial expressions. Using the NIR-LFC, the team acquired high-quality 3D reconstruction images of facial expressions expressing various emotions regardless of the lighting conditions of the surrounding environment.
The facial expressions in the acquired 3D images were distinguished through machine learning with an average of 85% accuracy – a statistically significant figure compared to when 2D images were used. Furthermore, by calculating the interdependency of distance information that varies with facial expression in 3D images, the team could identify the information a light-field camera utilizes to distinguish human expressions.
Professor Ki-Hun Jeong said, “The sub-miniature light-field camera developed by the research team has the potential to become the new platform to quantitatively analyze the facial expressions and emotions of humans.” To highlight the significance of this research, he added, “It could be applied in various fields including mobile healthcare, field diagnosis, social cognition, and human-machine interactions.”
Original Article: AI Light-Field Camera Reads 3D Facial Expressions?
More from: Korea Advanced Institute of Science and Technology
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Facial expression detection
- Advanced online biometrics applications explored by Humans.ai, Digital Domain, Kakao
Several developers in the biometrics space have made new announcements related to advanced applications powered by artificial intelligence.
- 27 Rights Groups Demand Zoom Abandon 'Invasive,' and 'Inherently Biased' Emotion Recognition Software
More than two dozen rights groups are calling on Zoom to scrap its efforts to explore controversial emotion recognition technology. The pushback from 27 separate groups represents some of the most ...
- More than two dozen human rights groups call on Zoom to halt emotion tracking software plans
The groups say the technology is discriminatory, manipulative, punitive, a data security risk and based on pseudoscience.
- Human Rights Groups Are Protesting Zoom's Emotion Recognition Tech
“Facial expressions are often disconnected from the emotions underneath ... At press time, Zoom had not publicly commented on the implementation of emotion recognition technology. The Fight for the ...
- Zoom must kill ‘creepy’ emotion tracking feature, human rights groups say
Human rights and privacy groups are demanding that video chat giant Zoom scrap its “creepy” plans to use artificial intelligence to track and analyze human emotions, slamming the technology as ...
Go deeper with Google Headlines on:
Facial expression detection
Go deeper with Bing News on:
Sub-miniature light-field camera
- Best unlocked phones 2022: choose any network or plan
Want a new phone and the freedom to choose your own network and SIM card? Check out our list of the very best unlocked phones ...
- Realme announces “best value 4G and 5G smartphones” and a new tablet
Realme has just revealed a range of new affordable products, including two new smartphones and a tablet. Here's what you need to know.
- 11 Best Body Cameras: Your Buyer’s Guide
It has a super wide-angle lens that will provide a field of view of 170-degrees ... a loud audible siren sound and flashes light. The days of mini spy cameras only appearing in spy movies and ...
- DJI’s new Mini 3 Pro drone hits the aerial photography sweet spot
DJI has just introduced a new drone — its most capable ever to squeak under the 250 gram limit that keeps operators free from a whole host of headaches and restrictions for flight (note that local ...
- DJI Mini 3 Pro Review: Setting a New High Bar For Travel Drones
The new DJI Mini 3 ... the upgraded camera. A 1/1.3-inch format sensor gives it 2.4 micron pixels when used at the default 12MP resolution. That helps its solid low-noise and low-light performance.