Google Street View To Pinpoint Businesses Using OCR

by Patrick Altoft on June 25, 2007

As if Google Street View wasn’t cool enough Bill Slawski has found a
patent application indicating that
Google might be able to use Optical Character recognition or OCR to
pinpoint the locations of thousands of businesses across the world.

At present the GPS coordinates are based on a particular street and
the actual coordinates of the individual addresses have to be
estimated. If you have ever tried adding your business to Google Local
you will probably have noticed the location was slightly inaccurate.
Google allows you to drag the location marker so you can pinpoint your
business but this method isn’t really scalable across thousands of
listings.

OCR isn’t new but it in the past it has been difficult for an
algorithm to figure out which parts of an street photo to read. This
latest patent looks at the picture and then does a database lookup to
see which businesses are expected and matches them up to the picture.
Once the business has been located in the picture the accurate GPS
coordinates can be updated on the database.

From the Database assisted OCR for street scenes and other images patent:

Optical character recognition (OCR) for images such as a
street scene image is generally a difficult problem because of the
variety of fonts, styles, colors, sizes, orientations, occlusions and
partial occlusions that can be observed in the textual content of such
scenes. However, a database query can provide useful information that
can assist the OCR process. For instance, a query to a digital mapping
database can provide information such as one or more businesses in a
vicinity, the street name, and a range of possible addresses. In
accordance with an embodiment of the present invention, this mapping
information is used as prior information or constraints for an OCR
engine that is interpreting the corresponding street scene image,
resulting in much greater accuracy of the digital map data provided to
the user.