|
Google to patent a way to index the world |
|
|
|
Written by Felix Da Silva (fdasilva@bitnip.com)
|
|
Saturday, 05 January 2008 |
In the patent application filed by Google at the World Intellectual Property Organization (WIPO), it suggests that it will be capable of indexing text on images and possibly video which allows the users to search the items in the content. Perhaps someday you will be able to take a picture of a room and it will index all the items in the room for search.
According to the application found here, its abstract states:
Methods, systems, and apparatus including computer program
products for using extracted image text are provided. In one implementation, a
computer-implemented method is provided. The method includes receiving an input
of one or more image search terms and identifying keywords from the received one
or more image search terms. The method also includes searching a collection of
keywords including keywords extracted from image text, retrieving an image
associated with extracted image text corresponding to one or more of the image
search terms, and presenting the image. It is actually a bit more complicated than just extracting text from an image. It actually looks at all the text that they are able to extract from the image in addition with other related keywords and put it into context.
The image database behind Google Maps Street View happens to contain many
street scenes of with this sort of text. Being able to query for store names
captured in Street View photos might be a useful way to conduct local searches.
In the patent application, it explains that
Digital images can include a wide variety of content. 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. This is certainly exciting because you can take a picture of a place and it will recognize what it is and index it. Instead of manually tagging every picture with keywords, you will be able to just do a search and be able to find exactly what you're looking for.
|