Envision announced several advanced features for its AI-powered Smart Glasses for the blind and visually impaired.
Envision’s newly launched functionalities include greater Optical Character Recognition (OCR), improved text reading with contextual intelligence, the addition of new languages, and the creation of a third-party app ecosystem allowing the “easy integration of specialist services, such as indoor and outdoor navigation,” to the Envision platform.
Developed on the Enterprise Edition of Google Glass, Envision made its debut at the 2020 CSUN Conference. It uses artificial intelligence (AI) to extract different kinds of information from images and then speaks the images out loud, enabling blind and low-vision users to read documents at work, recognize their friends, find personal belongings at home, use public transportation, and generally enjoy greater freedom, independence, and understanding of the world around them, according to the company’s announcement.
“Our mission is to improve the lives of the world’s two billion people who are blind or visually impaired by providing them with life-changing assistive technologies, products, and services,” said Karthik Kannan, co-founder of Envision. “By analyzing real-time user data and direct feedback from across our communities, we are able to constantly enrich the Envision experience and innovate our products, most recently with the addition of our new capture and context features. Everyone is entitled to live in a world without boundaries and are thrilled to make Envision Glasses to as many people as possible.”
Envision is available as an iOS and Android App and a Google Glass integration. According to Envision, it can read and translate any type of text (digital and handwritten) from any surface (eg, food packaging, posters, timetables, computer display screens, barcodes, etc..) into over 60 different languages. It can recognize faces, objects, and colors, and even describe scenes and connect users to contacts through its Ally function – a private video call solution built directly into the glasses. You can see it in action here.
Envision’s new features include:
- Document Guidance for Accurate Capture – Removes the frustrations of taking multiple images to fully capture a document’s complete text. Enhanced document guidance helps “provide verbal instructions to guide users to position documents to the optimal scanning position allowing capture in a single motion.”
- Layout Detection – Helping to provide “a more realistic reading environment,” Envision smart glasses will now help put a document into context for the reader. Whether a column-based document such as a newspaper, a shop window poster, road sign, or restaurant menu, Envision will “decipher the document layout and provide clear verbal guidance to the user.” It recognizes headers, photo captions, and more, giving verbal layout context to the user, enabling a more natural flow to the audio read back of the document, the company says.
- Enhanced Offline Language Capabilities– Envision now adds four additional Asian languages, including Hindi, Japanese, Chinese, and Korean, which can be accurately captured and read offline. This addition brings the total of languages supported when offline to 26, with the number of languages supported when connected to more than 60.
- Third-Party App Development Support – Envision now adds a third-party ecosystem to its platform by allowing developers to build added value services to its users. Launching with the initial partner Cash Reader app, Envision can now recognize banknotes in over 100 currencies.
- Building Ally – One of the Envision Glasses’ “most powerful and popular features” is the Ally function that enables a user to ask for assistance or share experiences with trusted contacts (Allys) via private video calls directly from the glasses. The new, improved version is optimized for both mobile network and WiFi hotspots, according to Envision.
- Optimizing Optical Character Recognition (OCR) – Leveraging tens of millions of data points processed by the Envision Glasses and apps has “significantly improved image capture and interpretation accuracy.”