Patent: face recognition, image search, and apps among the potential Google Glass features

December 17, 2012

    bits-projectglass-tmagArticle

    The US Patent and Trademark Office has just published a new patent application by Google related to its Project Glass. The patent hints at the many possible features of Google’s futuristic head mounted device. Among the features that have been detailed, the most intriguing include apps, image search, and facial recognition.

    According to Patent Bolt, the patent application details the so-called multimode feature of the Glass. The multimode feature is an input field that could display a number of different types of content in front of the user’s eye, based on the different kinds of input received by the device. The input sources could include text, text corresponding to speech, audio signal etc. The multimode input field can be used to perform image searches, face recognition, contact look up, editing documents, or sending an email.

    The field will be resizable and adjustable according to the user’s liking, just like windows on a Windows or Mac computer.

    Google also wants to take the simple drag and drop feature and optimize it for its Project Glass. The application reveals that the action may be performed on a touchpad that would control the drag and drop action on the display, which is pretty much similar to how it’s done on a laptop. Google also states that the drag and drop instructions may also correspond to other gestures and input methods, including keystrokes on a keyboard, a voice command, hand gestures detected in a video feed and others.

    Another feature that has been detailed in this patent application is the viewfinder. In the viewfinder mode, a multimode window may be adjusted using pinch-to-zoom or other gestures and even moved to a new location in the display to make room for other things. The viewfinder could come in handy when the user wants to do a specific action on a certain region of the field of view – for instance, one could snap a picture of a certain, zoomed in area, or scan a certain portion of text using the viewfinder.

    google glass viewfinder

    The patent application also details the image search feature that could be initiated with a gesture like a double tap. Face recognition feature is also mentioned in the application, a function that will allow users to identify a person in the viewfinder mode by looking at his or her face. Obviously, the potential for this feature is wide open – from law enforcement agents to club bouncers, anyone could check the ID of a person with a blink of an eye.

    Other features mentioned in the Project Glass patent application include ability to take snapshots from the playing video and support for apps. Google is planning to allow third party developers to create different kinds of applications for the futuristic device. Possible built-in apps detailed in the application are a music app (similar to the What’s this song? feature in Android 4.2), an airline app that could display information on a flight based on specific inputs, or  a movie app, which would turn the Glass into a head-mounted cinema.

    Google Glass shapes out to be very exciting and we can’t wait to see what Sergey Brin is preparing for the next Google I/O!

    Comments

    • dlb

      How ’bout a Star Wars-like electronic zooming binoculars

    • http://twitter.com/PheonixElliott Elliott Hyde

      It would be very cool if it could be made as a glasses mount (something that you attach to your vision corrective glasses) or maybe even built into the lens!

    • http://www.facebook.com/illogical06 Clayton Clayborn

      Probably not in generation 1 of these glasses but the implications are impressive with these patents.

      Your glasses could be set up to where if any persons face is within view for X amount of time, it will see it as an area of focus from the viewer and run the facial recognition software and post their Facebook info, google search, etc in real time with 0 effort from the user. Instant knowledge.

      The image search is equally as incredible. The device will or eventually will recognize gestures from the viewer. So you could pinch or zoom around what you see and create a selection box similar to that we do with mouses or touch screens. Only in the area and when you stop, the glasses immediately perform a search of the image created by the gesture and post it in your field of vision.

    Popular

    Latest