Patent: Google May Categorize Images Using Object Recognition, Optical Character Recognition(OCR) and More

Bill Slawski breaks down a newly granted Google patent Image analysis for results of textual image queries that sheds some light on how Google may use textual image queries and how they may classify images.

Google may categorize images using object recognition, Optical Character Recognition(OCR), etc to determine what to show of an image or may analyze text that appears in an image to create categories. Those categories can determine what an image may rank for in image search results.

Key points:

• This new patent is about returning image search results for textual image queries. The patent tells us how Google processes those textual image queries. This image query processing system classifies images and use uses those image categories to decide which images to return that are responsive to a textual image query.
• When the image query processing system receives a textual image query from a searcher, it may decide on one or more categories from many different image categories that are likely to include images that are responsive to the textual image query.
• The textual image queries processing system may then analyze images in the categories to choose images responsive to the textual image query and display the selected images in search results.

He unpacks a lot of info on the process from things like

• Using Key Phrases From the Textual Image Queries
• Cropping Content From an Image that is Not Responsive to a Textual Image Query
• and more

Like with all of the other patent posts from Bill, this is well worth have a read through.