Recognizing Text on Images and Videos: Google Applies for Patent

An interesting feature by SE Roundtable on an InformationWeek article about Google applying for patent on its technology that enables it to read text beyond the conventional means.

This sounds so interesting and yet, it impacts several things.

“Recognizing Text In Images” is an application to patent a method of optical character recognition in digital images.

“Digital images can include a wide variety of content,” the patent application explains. “For example, digital images can illustrate landscapes, people, urban scenes, and other objects. Digital images often include text. Digital images can be captured, for example, using cameras or digital video recorders. Image text (i.e., text in an image) typically includes text of varying size, orientation, and typeface. Text in a digital image derived, for example, from an urban scene (e.g., a city street scene) often provides information about the displayed scene or location. A typical street scene includes, for example, text as part of street signs, building names, address numbers, and window signs.”

Local search may now be easier as this convenience is not only brings relief to people whose text contents are buried within images. The technology is also applicable to maps or videos. Imagine if you can search for text that’s found in YouTube or a shop that appears within a Google Map. Advanced text recognition technology could spawn a plethora of applications based on Google’s capabilities:

“For example, a user enters a search for a McDonald’s in a particular city or near a particular address,” the patent application suggests. “The mapping application generates a map to the McDonald’s as well as presents an image of the McDonald’s. The McDonald’s image is retrieved using the indexed text from the image identifying the McDonald’s and location information associated with the image, which identifies the location of the particular McDonald’s in the image.”

Or, synonymous to having Google Street View by having camera-equipped vehicles drive through urban areas to capture a series of images of the trip, a new product might be called Google Product View will be capable of doing something like scanning through product shelves of a supermarket and associate them with the shop where they are found.

I imagine these things as so futuristic but not impossible to achieve.