×

Image retrieval systems and methods with semantic and feature based relevance feedback

  • US 7,499,916 B2
  • Filed: 10/20/2004
  • Issued: 03/03/2009
  • Est. Priority Date: 10/30/2000
  • Status: Expired due to Fees
First Claim
Patent Images

1. A computer-readable medium having computer-executable instructions for performing steps comprising:

  • initiating a search for images based on at least one query keyword in a query,wherein the search further comprises;

    identifying, during the search, first images having associated keywords that match the query keyword;

    extracting low-level features from the first images; and

    identifying second images using pattern matching that contain the low-level features similar to those of the first images, wherein the low-level features comprise color, shape, and texture and the low-level features do not match the search query;

    ranking the first and second images;

    presenting the first and second images to a user, wherein the second image is an example image; and

    receiving feedback from the user as to whether the first and second images are relevant to the query further comprising;

    assigning a first weight to an association between the query keyword and the first images deemed relevant by the user and/or assigning a second weight to an association between the query keyword and the example image, in order to rank the images, wherein the first weight is greater than the second weight; and

    storing the first weight and/or second weight on a computer-readable medium.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×