Method and mechanism for retrieving images

• US 7,831,111 B2
• Filed: 12/22/2005
• Issued: 11/09/2010
• Est. Priority Date: 10/31/2005
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Shah, Shesha, Sathish, Sriram J.
• Primary Examiner(s): Le; Brian Q
• Assistant Examiner(s): BEKELE, MEKONEN T
• Application Number:
  US11/317,952
• Publication Number:
  US 20070097420A1
• Time in Patent Office: 1,783 Days
• Field of Search: 358/403, 709/200, 709/206, 709/204, 709/231, 709/219, 382/305, 348/36, 348/240, 348/143, 348/159
• US Class Current: 382/305
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content

Abstract

A method and apparatus for, in response to receiving a request, retrieving digital images that are associated with one or more keywords and which are similar to a digital image is provided. The request may be processed using a keywords index and a content index, and optionally, a session index that references data about what digital images users have viewed together in a session. A category associated with the identified digital image may also be used in processing the request, e.g., the category associated with the identified digital image may change the weight placed on various content attributes used in comparing the content of the identified digital image to other digital images. After the set of requested digital images are determined, request data, that identifies the set of requested digital images, may be sent to the requestor.

Claims

1. A method for retrieving digital images, comprising:

while images are viewed in a plurality of Transmission Control Protocol/Internet Protocol (TCP/IP) sessions, storing data that indicates which images are viewed in same sessions;

wherein the data indicates that a first set of images were viewed in one or more sessions in which a particular image was also viewed;

wherein the data indicates that a second set of images were not viewed in any session in which the particular image was also viewed;

receiving, from a client, request data that specifies search criteria;

wherein the search criteria identifies the particular image as a base image;

in response to receiving the request data, performing the steps of;

reading the data to determine that the first set of images, but not the second set of images, were viewed in one or more sessions in which said base image was also viewed,

selecting one or more requested images based, at least in part, on whether the images were viewed in sessions in which said base image was also viewed,

wherein images in the first set are more likely to be selected than images in the second set because the images in the first set were viewed in one or more sessions in which said base image was also viewed; and

transmitting, to the client, response data that identifies the one or more requested images;

wherein the step of selecting one or more requested images is performed by one or more computing devices.

2. The method of claim 1, wherein the response data includes the one or more requested images.

3. The method of claim 1, further comprising:

determining a particular category, of a plurality of categories, associated with the base image,

wherein selecting the one or more requested images includes selecting the one or more requested images based, at least in part, on whether images are associated with the particular category.

4. The method of claim 3, wherein each category, of the plurality of categories, is associated with a set of attribute weight values, and wherein each of the set of attribute weight values describes how much weight a particular content attribute should be assigned when comparing an image description data to a content data.

5. The method of claim 1, wherein selecting the one or more requested images further comprises:

determining that a new image should be included in the one or more requested images, or determining that an existing image should be included in the one or more requested images, based upon session data, wherein the session data identifies images which one or more users viewed together during a single TCP/IP session of a specified duration.

6. The method of claim 1, wherein selecting the one or more requested images is performed, at least in part, on session data, wherein the session data identifies images which one or more users viewed together during a single TCP/IP session of a specified duration.

7. The method of claim 6, wherein the specified duration expires at one or more of:

(a) a time interval, and (b) receipt of another request, from the client, for requested images.

8. The method of claim 6, wherein the session data is organized in a session index, wherein each entry of the session index indicates, for the particular image, other images which one or more users viewed together with the particular image during the single session of a specified duration.

9. The method of claim 1, wherein the server stores keyword data that associates keywords with the base image, wherein the request data identifies the one or more keywords by identifying the base image, wherein the request data does not contain the one or more keywords, and wherein the method further comprises:

the server determining the one or more keyword based upon the keyword data.

10. The method of claim 1, wherein the request data identifies a set of criteria, and wherein the one or more requested images is created by removing those images which do not match the set of criteria.

11. The method of claim 1, wherein selecting the one or more requested images further comprises:

ranking each image in a set of requested images based on how similar content of each image is to content of the base image, thereby creating one or more ranked images.

34. The method of claim 1, wherein the request data further requests one or more requested images that are associated with one or more keywords;

and

wherein selecting the one or more requested images is based, at least in part, on whether the images are associated with said one or more keywords.

35. The method of claim 1, further comprising:

generating a content index comprising a plurality of entries for indexed images, wherein each of the plurality of entries contains image description data that reflects one or more content attributes of one of the indexed images;

analyzing the base image to determine content data, wherein the content data reflects one or more content attributes of the base image;

determining the one or more requested images by;

for each image of a plurality of images that are indexed by said content index, performing a comparison of an image description data, associated with an entry of the content index for that image, with the content data, thereby determining how similar content of each image is to content of the base image, and

selecting one or more additional requested images based, at least in part, on (a) said comparison, and (b) whether the images were viewed in the same session as said base image; and

transmitting, to the client, second response data that identifies the one or more additional requested images.

12. A machine-readable non-transitory storage storing one or more sequences of instructions for retrieving digital images, wherein execution of the one or more sequences of instructions by one or more processors cause:

while images are viewed in a plurality of Transmission Control Protocol/Internet Protocol (TCP/IP) sessions, storing data that indicates which images are viewed in same sessions;

wherein the data indicates that a first set of images were viewed in one or more sessions in which a particular image was also viewed;

wherein the data indicates that a second set of images were not viewed in any session in which the particular image was also viewed;

receiving, from a client, request data that specifies search criteria;

wherein the search criteria identifies the particular image as a base image;

in response to receiving the request data, performing the steps of;

reading the data to determine that the first set of images, but not the second set of images, were viewed in one or more sessions in which said base image was also viewed,

selecting one or more requested images based, at least in part, on whether the images were viewed in sessions in which said base image was also viewed,

wherein images in the first set are more likely to be selected than images in the second set because the images in the first set were viewed in one or more sessions in which said base image was also viewed; and

transmitting, to the client, response data that identifies the one or more requested images.

13. The machine-readable storage of claim 12, wherein the response data includes the one or more requested images.

14. The machine-readable storage of claim 12, wherein execution of the one or more sequences of instructions by the one or more processors further cause:

determining a particular category, of a plurality of categories, associated with the base image,

wherein selecting the one or more requested images includes selecting the one or more requested images based, at least in part, on whether images are associated with the particular category.

15. The machine-readable storage of claim 14, wherein each category, of the plurality of categories, is associated with a set of attribute weight values, and wherein each of the set of attribute weight values describes how much weight a particular content attribute should be assigned when comparing an image description data to a content data.

16. The machine-readable storage of claim 12, wherein selecting the one or more requested images further comprises:

determining that a new image should be included in the one or more requested images, or determining that an existing image should be excluded from the one or more requested images, based upon session data,

wherein the session data identifies images which one or more users viewed together during a single TCP/IP session of a specified duration.

17. The machine-readable storage of claim 12, wherein selecting the one or more requested images is performed, at least in part, on session data, wherein the session data identifies images which one or more users viewed together during a TCP/IP single session of a specified duration.

18. The machine-readable storage of claim 17, wherein the specified duration expires at one or more of:

(a) a time interval, and (b) receipt of another request, from the client, for requested images.

19. The machine-readable storage of claim 17, wherein the session data is organized in a session index, wherein each entry of the session index indicates, for the particular image, other images which one or more users viewed together with the particular image during the single session of a specified duration.

20. The machine-readable storage of claim 12, wherein the server stores keyword data that associates keywords with the base image, wherein the request data identifies the one or more keywords by identifying the base image, wherein the request data does not contain the one or more keywords, and wherein the method further comprises:

the server determining the one or more keyword based upon the keyword data.

21. The machine-readable storage of claim 12, wherein the request data identifies a set of criteria, and wherein the one or more requested images is created by removing those images which do not match the set of criteria.

22. The machine-readable storage of claim 12, wherein selecting the one or more requested images further comprises:

ranking each image in a set of requested images based on how similar content of each image is to content of the base image, thereby creating one or more ranked images.

36. The machine-readable storage of claim 12, wherein execution of the one or more sequences of instructions by the one or more processors further cause:

generating a content index comprising a plurality of entries for indexed images, wherein each of the plurality of entries contains image description data that reflects one or more content attributes of one of the indexed images;

analyzing the base image to determine content data, wherein the content data reflects one or more content attributes of the base image;

determining the one or more requested images by;

for each image of a plurality of images that are indexed by said content index, performing a comparison of an image description data, associated with an entry of the content index for that image, with the content data, thereby determining how similar content of each image is to content of the base image, and

selecting one or more additional requested images based, at least in part, on (a) said comparison, and (b) whether the images were viewed in the same session as said base image; and

transmitting, to the client, second response data that identifies the one or more additional requested images.

23. An apparatus for retrieving digital images, comprising:

a non-transitory machine-readable storage storing one or more sequences of instructions; and

one or more processors, wherein execution of the one or more sequences of instructions by the one or more processors causes;

while images are viewed in a plurality of Transmission Control Protocol/Internet Protocol (TCP/IP) sessions, storing data that indicates which images are viewed in same sessions;

wherein the data indicates that a first set of images were viewed in one or more sessions in which a particular image was also viewed;

wherein the data indicates that a second set of images were not viewed in any session in which the particular image was also viewed;

receiving, from a client, request data that specifies search criteria;

wherein the search criteria identifies the particular image as a base image;

in response to receiving the request data, performing the steps of;

reading the data to determine that the first set of images, but not the second set of images, were viewed in one or more sessions in which said base image was also viewed,

selecting one or more requested images based, at least in part, on whether the images were viewed in sessions in which said base image was also viewed,

wherein images in the first set are more likely to be selected than images in the second set because the images in the first set were viewed in one or more sessions in which said base image was also viewed; and

transmitting, to the client, response data that identifies the one or more requested images.

24. The apparatus of claim 23, wherein the response data includes the one or more requested images.

25. The apparatus of claim 23, wherein execution of the one or more sequences by the one or more processors further cause:

determining a particular category, of a plurality of categories, associated with the base image,

wherein selecting the one or more requested images is based, at least in part, on selecting images that are associated with the particular category.

26. The apparatus of claim 25, wherein each category, of the plurality of categories, is associated with a set of attribute weight values, and wherein each of the set of attribute weight values describes how much weight a particular content attribute should be assigned when comparing an image description data to the content data.

27. The apparatus of claim 23, wherein selecting the one or more requested images further comprises:

adding a new image to a set of requested images or removing an existing image from the set of requested images based upon session data,

wherein the session data identifies images which one or more users viewed together during a single TCP/IP session of a specified duration.

28. The apparatus of claim 23, wherein selecting the one or more requested images is performed, at least in part, on session data, wherein the session data identifies images which one or more users viewed together during a single TCP/IP session of a specified duration.

29. The apparatus of claim 28, wherein the specified duration expires at one or more of:

(a) a time interval, and (b) receipt of another request, from the client, for requested images.

30. The apparatus of claim 28, wherein the session data is organized in a session index, wherein each entry of the session index indicates, for the particular image, other images which one or more users viewed together with the particular image during the single session of a specified duration.

31. The apparatus of claim 23, wherein the server stores keyword data that associates keywords with the base image, wherein the request data identifies the one or more keywords by identifying the base image, wherein the request data does not contain the one or more keywords, and wherein the method further comprises:

the server determining the one or more keyword based upon the keyword data.

32. The apparatus of claim 23, wherein the request data identifies a set of criteria, and wherein the one or more requested images is created by removing those images which do not match the set of criteria.

33. The apparatus of claim 23, wherein selecting the one or more requested images further comprises:

ranking each image in a set of requested images based on how similar content of each image is to content of the base image, thereby creating one or more ranked images.

37. The apparatus of claim 23, wherein execution of the one or more sequences by the one or more processors further cause:

generating a content index comprising a plurality of entries for indexed images, wherein each of the plurality of entries contains image description data that reflects one or more content attributes of one of the indexed images;

analyzing the base image to determine content data, wherein the content data reflects one or more content attributes of the base image;

determining the one or more requested images by;

for each image of a plurality of images that are indexed by said content index, performing a comparison of an image description data, associated with an entry of the content index for that image, with the content data, thereby determining how similar content of each image is to the content of the base image, and selecting one or more additional requested images based, at least in part, on (a) said comparison, and (b) whether the images were viewed in the same session as said base image; and

transmitting, to the client, second response data that identifies the one or more additional requested images.