In Brief
Google has announced Airfinger, an AI-powered gesture recognition system that will allow users to interact with the web in real time using hand gestures.
It uses a combination of computer vision and machine learning to accurately recognize hand gestures, making it more affordable and accessible to a wider range of users.
Airfinger is currently capable of recognizing seven different gestures, but Google is already working on expanding its repertoire.
The Trust Project is a worldwide group of news organizations working to establish transparency standards.
Google has announced a new AI-powered gesture recognition system that will allow users to interact with the web in real time using only hand gestures. The system, called Airfinger, is still in early development but has the potential to revolutionize the way we interact with our devices.
Airfinger uses a combination of computer vision and machine learning to accurately recognize hand gestures, making it possible to navigate websites, play games, and control smart home devices without ever touching a screen or keyboard. This technology could also have significant implications for accessibility, allowing people with disabilities to use mobile devices in new ways.
Airfinger uses the same basic principle as other gesture recognition systems, such as Microsoft Kinect or the Leap Motion Controller. However, instead of using a dedicated piece of hardware, Airfinger uses the front-facing camera on a smartphone or tablet. This makes it much more affordable and accessible to a wider range of users. Airfinger’s use of the front-facing camera on a smartphone or tablet also means that it can be used on the go, making it ideal for presentations or meetings where a traditional gesture recognition system may not be available or practical. Additionally, the software is constantly being updated to improve its accuracy and expand its range of compatible devices.
At the moment, Airfinger is only capable of recognizing seven different gestures: 👍, 👎, ✌️, ☝️, ✊, 👋, and 🤟. However, Google is already working on expanding its repertoire. The company is also working on improving the accuracy of the system, as well as its ability to work in low-light conditions. Google’s goal is to make Airfinger capable of recognizing more complex gestures and, eventually, sign language. This would greatly benefit people with disabilities who rely on sign language as their primary means of communication.
Mediapipe can recognize such gestures with the default training model:
- Closed fist (
Closed_Fist) - Open palm (
Open_Palm) - Pointing up (
Pointing_Up) - Thumbs down (
Thumb_Down) - Thumbs up (
Thumb_Up) - Victory (
Victory) - Love (
ILoveYou)
Google has made it available to the public on GitHub. However, the fact that it is already being worked on by the company’s R&D team suggests that it is a priority for Google. With any luck, we will see Airfinger roll out to devices in the near future.
Read more about AI:
Disclaimer
Any data, text, or other content on this page is provided as general market information and not as investment advice. Past performance is not necessarily an indicator of future results.
