Whenever I shop online, the first thing I do is set the Web site’s filters (assuming they are provided) to quickly locate the type of product or brand that I’m looking for. IBM is developing an augmented reality mobile shopping application that may soon make it possible to do the same in stores.

At IBM’s Smarter Commerce Global Summit last week, I saw the Augmented Shopping Advisor in action. Amnon Ribak, the project’s leader, held an iPad in front of a blown up image of cereal boxes to demonstrate how the app can filter the cereals by brand and other preferences like whole wheat or low fat, as well as display recommendations and offers.

The app, which was developed by researchers at IBM’s lab in Israel, uses algorithms that combine techniques used in facial recognition, color and shape matching, and associations with surrounding products. No bar codes or RFID tags are needed. The app also takes into account the mobile device’s camera angle and distance from a shelf to distinguish between products.

In addition to helping shoppers, the app can also help retailers gain insight into what their customers look for when shopping and quickly find out which products need to be restocked. Several retailers have expressed interest in testing the tool, according to Ribak.

See for yourself how the app works in the video below: