Analyzing images to determine if one or more sets of materials correspond to the analyzed images

• US 6,785,421 B1
• Filed: 05/22/2000
• Issued: 08/31/2004
• Est. Priority Date: 05/22/2000
• Status: Expired due to Term

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Zhu, Wei, Mehrotra, Rajiv, Gindele, Edward B.
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US09/576,558
• Time in Patent Office: 1,562 Days
• Field of Search: 382/118, 382/190, 382/217, 382/218, 382/224-225, 707/2-6, 705/14, 709/219
• US Class Current: 382/217
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/5862 using texture
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A method of analyzing one or more images of a user to determine the likelihood of user interest in materials that can be sent for display to the user includes selecting one or more images by a user; automatically analyzing the one or more user images to determine the likelihood that materials in a set will be of interest to the user; and selecting one or more items of materials based on their likelihood of interest to the user.

Claims

1. A method of analyzing one or more images of a user to determine the likelihood of user interest in product or promotional materials that can be sent to the user, comprising:

a) selecting one or more images having pixels by a user;

b) providing a plurality of product and promotional materials;

c) automatically analyzing, without using the product or promotional materials, the pixels of the one or more user images to determine the likelihood that one or more particular product or promotional materials will be of interest to the user; and

d) selecting one or more of the product or promotional materials based on their likelihood of interest to the user.

2. A computer storage product having at least one computer storage medium having instructions stored therein causing one or more computers to perform the method of claim 1.

3. A method of analyzing one or more images of a user to determine the likelihood of user interest in product or promotional materials that can be sent to the user, comprising:

a) receiving one or more user images having pixels from the user;

b) storing in a database sets of database images, and sets of product or promotional materials, wherein each set of product or promotional materials corresponds to a different set of database images;

c) automatically analyzing the pixels of the one or more user images and the received database images to determine based upon the analysis if there is a likelihood that one or more of sets of product or promotional materials will be of interest to the user; and

d) selecting the one or more likely sets of product or promotional materials based on their likelihood of interest to the user.

4. The method of claim 3 further including:

e) automatically extracting a representation from the one or more sets of database images in terms of one or more features that characterize the one or more sets of database images; and

f) storing the one or more sets of database image and the representation in a database.

5. The method according to claim 4 wherein features are color or texture.

6. The method of claim 3 wherein the one or more sets of product or promotional materials includes services.

7. The method of claim 3 wherein the one or more sets of product or promotional materials include at least one website.

8. The method of claim 3 wherein the analysis includes performing an image similarity calculation with respect to the user images and database images.

9. The method of claim 3 further including sending the one or more selected product or promotional materials to the user.

10. The method of claim 3 further including automatically extracting representations from the received user images in terms of one or more features that characterize the user images and storing the received user images and the extracted representations in a database.

11. The method according to claim 10 wherein features are color or texture.

12. The method of claim 3 further including automatically extracting from the one or more sets of database images in terms of one or more perceptually significant depictive features that dominate a perception of the one or more sets of database images and storing the one or more sets of database images and the extracted representations in a database.

13. The method according to claim 12 wherein features are color or texture.