Selecting images using associated keywords

1. A computer-implemented method for selecting from a plurality of stored images one or more images similar to a first image, the stored images and the first image each having a plurality of stored keywords associated therewith, the method comprising:

responsive to a request by a user to see similar images:

calculating, by one or more processors, a keyword score for each stored keyword associated with the first image, each keyword score being based only on the number of stored images associated with that keyword;

calculating, by one or more processors, an image similarity score for at least some of the stored images, each image similarity score being based on the keyword scores of the stored keywords associated with both that image and the first image; and

selecting, by one or more processors, one or more of the stored images having the highest image similarity scores and providing the selected images for displaying to the user;

each keyword score being calculated based on the inverse logarithm of the total number of images having the respective keyword associated therewith; and

each image similarity score being calculated by summing the keyword scores for all keywords associated with the respective image, and wherein an image similarity score is calculated only for those stored images having at least one stored keyword that is also a stored keyword of the first image.

2. The method of claim 1 wherein the first image is one of the stored images.

3. The method of claim 2 wherein the first image is selected by a user from a plurality of stored images displayed to the user.

4. The method of claim 1 wherein the first image is selected based on keywords provided by a user.

5. The method of claim 1 further comprising assigning a default keyword score to all keywords associated with the at least some of the stored images that are not keywords associated with the first image.

6. The method of claim 1 wherein the image similarity score for each image is determined by summing the keyword scores of the keywords associated with that image.

7. The method of claim 5 wherein the default keyword score is zero.

8. A method of operating a server system in communication with a client system, the server system having access to a plurality of stored images, each stored image having a plurality of stored keywords associated therewith, the method comprising:

in response to a request by the user at a client system to see similar images to a first

image in the plurality of stored images, performing the following steps:

calculating, by one or more processors, a keyword score for each stored keyword associated with the first image, each keyword score being based only on the number of stored images associated with that keyword;

calculating, by one or more processors, an image similarity score to at least some of the stored images, each similarity score being based on the keyword scores of the stored keywords that are associated with both that image and the first image; and

selecting one or more stored images having the highest image similarity scores and providing the selected images for displaying to the user;

each keyword score being calculated based on the inverse logarithm of the total number of images having the respective keyword associated therewith; and

each image similarity score being calculated by summing the keyword scores for all keywords associated with the respective image, and wherein an image similarity score is calculated only for those stored images having at least one stored keyword that is also a stored keyword of the first image.

9. The method of claim 8 wherein the first image is selected by the user of the client system.

10. The method of claim 1 wherein an image similarity score is assigned only to those stored images having at least one stored keyword that is also a stored keyword of the first image.

11. The method of claim 5 wherein the image similarity score for a stored image is determined by summing the keyword scores of the keywords that are associated with both that image and the first image.

12. One or more non-transitory computer readable storage encoded with computer executable instructions for performing the method of claim 1 .

13. The method of claim 8 wherein an image similarity score is assigned only to those stored images having at least one stored keyword that is also a stored keyword of the first image.

14. The method of claim 9 wherein the first image is selected from a plurality of stored images displayed to a user.

15. The method of claim 8 wherein the first image is selected based upon keywords provided by a user.

16. The method of claim 8 further comprising assigning a default keyword score to all keywords associated with the at least some of the stored images that are not keywords associated with the first image.

17. The method of claim 16 wherein the image similarity score for each image is determined by summing the keyword scores of the keywords associated with that image.

18. The method of claim 16 wherein the default keyword score is zero.

19. The method of claim 8 wherein one or more of the one or more selected stored images are provided to the client system for displaying to the user.

20. One or more non-transitory computer readable storage encoded with compute executable instructions for performing the method of claim 8 .

21. A system for selecting one or more images similar to a first image, comprising:

one or more processing units configured to receive a selection by a user of the first image from a plurality of stored images, the stored images and the first image each having one or more stored keywords associated therewith;

one or more processing units configured to receive a request by the user to see similar images to the first image;

one or more processing units configured to calculate, upon receipt of the request by the user to see similar image to the first image, a keyword score for each stored keyword associated with the first image, to determine an image similarity score for at least some of the stored images, and to select one or more of the stored images as similar to the first image based on the image similarity scores of the stored images, each keyword score being based only on the number of stored images associated with that keyword, and each image similarity score being based on the keyword scores of the stored keywords associated with both that image and the first image;

each keyword score being calculated based on the inverse logarithm of the total number of images having the respective keyword associated therewith, and each image similarity score being calculated by summing the keyword scores for all keywords associated with the respective image, and wherein an image similarity score is calculated only for those stored images having at least one stored keyword that is also a stored keyword of the first image.

22. A computer-implemented method for selecting one or more images similar to a first image from a plurality of stored images each having one or more stored keywords associated therewith, the method comprising:

responsive to a request by the user of a selection of the first image from a plurality of stored images and a request by the user to see similar images, performing the following steps:

for each respective keyword associated with the first image, determining by one or more processors the total number of stored images associated with the respective keyword;

calculating by one or more processors a keyword score for each respective keyword associated with the first image based only on the total number of stored images associated with the respective keyword based on computation of an inverse logarithm of the total number of images that are associated with the respective keyword;

determining an image similarity score for at least some of the stored images by summing the keyword scores for all keywords associated with that image; and

selecting one or more of the stored images as similar to the first image based on the image similarity scores of the stored images.

23. A system for selecting from a plurality of stored images one or more images similar to a first image from a plurality of stored images each having one or more stored keywords associated therewith, comprising:

one or more processing units configured to receive a request by the user of a selection of the first image from a plurality of stored images and a request by the user to see similar images, and in response to the request;

one or more processing units to determine the total number of stored images associated with the respective keyword for each respective keyword associated with the first image,

one or more processing units to determine a keyword score for each respective keyword associated with the first image based on the inverse logarithm of the total number of stored images associated with the respective keyword,

one or more processing units to determine an image similarity score for at least some of the stored images by summing the keyword scores for all keywords associated with that image, and

one or more processing units to select as similar to the first image one or more of the stored images based on the image similarity scores of the stored images.