The combination of artificial intelligence and Google Glass is fueling a new era of independence for the visually impaired by allowing them to autonomously interact with the world around them.
Thanks to advances in multi-modal systems and generative artificial intelligence models, it is now possible for blind people to explore and understand their environment in completely new ways.
A prominent example of this technology is Ask Envision, a digital tool that acts as a virtual assistant capable of viewing and analyzing the environment using state-of-the-art artificial intelligence algorithms, such as GPT-4, to provide real-time information through a computer generated voice.
With the aim of providing a comfortable and unrestricted experience, Envision developers have chosen Google Glass as the ideal support device.
These smart glasses, equipped with artificial intelligence, give users the ability to navigate the streets seamlessly, without having to deal with the need to use large virtual reality glasses in the middle of a park or a supermarket.
The lightness of Google Glass and its long battery life make it the perfect choice for public environments.
Thanks to the Envision application, the system allows you to recognize faces, objects, colors and even describe scenes and environments, all transmitted through an artificial voice that is heard directly from the Google glasses.
It is important to mention that the processing of the environment is based on the capture of static images taken by users.
To access this artificial intelligence technology, each user must install the Envision AI application on their mobile phone and link it to Google Glass.
Once this is done, you can access voice commands like “Scan this” and touch gestures, like touching the side of the glasses to capture a photo and start the scan.
The versatility of the artificial intelligence built into Google Glass is impressive. According to the developers, this technology is capable of identifying other people in a room and providing information about their physical appearance.
In addition, it can translate text into more than 60 different languages and recognize banknotes from more than 100 different countries, making it easy to travel and interact in international destinations.
It is important to note that while these facial recognition, environmental interpretation, and text translation features are valuable for visually impaired users, their use must be controlled and limited to specific activities.
Although artificial intelligence has advanced significantly, there are still challenges regarding the accuracy and reliability of the information provided.