System and method for advertising using image search and classification

An advertising system comprising:

• memory which stores an advertising template for an advertising sponsor;
• memory which stores:
• a categorizer for categorizing a set of a user's images, based on image content, the categorizer including at least one classifier which has been trained on image signatures of a labeled set of training images, the labels being selected from a finite set of image categories;
• a comparison computing component for selecting an advertising image based on the categorization of the user's images;
• and
• a combing component for combining the template with the selected advertising image to form advertising content which is displayable to the user on a web page viewed by the user;
• and
• a computer processor which implements the categorizer, comparison computing component, and combining component.

A method comprising:

• for a user viewing a web page, generating a user profile comprising categorizing a set of the user's images, based on image content of the images in the set, with at least one classifier which has been trained on a finite set of image categories, the user profile represents a distribution of the user images over at least a set of the categories;
• with a computer processor, performing at least one of:
• a) selecting an image for an advertisement to be displayed to the user on the web page, based on the user profile;
• b) displaying information to the user based on the user profile;
• c) comparing the user profile with a user profile for at least one other user and outputting a decision based on the comparison, wherein the decision is optionally based on a GPS location of at least one of the user and the at least one other user;
• d) using the profile in a recommender system to make recommendations to the user;
• and
• e) making a financial decision based on the user profile.