Reduction of search ambiguity with multiple media references

• US 9,684,675 B2
• Filed: 09/30/2002
• Issued: 06/20/2017
• Est. Priority Date: 09/30/2002
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Wilensky, Gregg D.
• Primary Examiner(s): Beausoliel, Jr., Robert
• Assistant Examiner(s): BROMELL, ALEXANDRIA Y
• Application Number:
  US10/526,287
• Publication Number:
  US 20060074861A1
• Time in Patent Office: 5,377 Days
• Field of Search: 707708, 707723, 707736, 707748, 707758, 707915, 382218
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/56 having vectorial format
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/24133 Distances to prototypes
• CPC Class Codes: G06T 7/40 Analysis of texture depth or shape recovery from texture G06T7/529
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects

Abstract

Methods and apparatus implementing a technique for searching media objects. In general, in one aspect, the technique includes receiving user input specifying a plurality of reference objects (2), defining a set of features for them, and combining the features to generate composite reference information (4) defining criteria for search (6). In general, in another aspect, the technique includes combining object information for a plurality of reference objects to produce composite reference information, comparing (10) the composite reference information to object information for media objects in a collection of media objects, and selecting a media object based upon the comparison.

Claims

1. A computer-implemented method comprising:

receiving a plurality of reference images;

calculating by a computer image parameters for each reference image wherein the image parameters characterize color, texture and shape features that are common to the reference image and at least one other reference image;

combining by the computer the calculated image parameters to generate a composite reference image; and

comparing by the computer the composite reference image to images in a collection in order to identify one or more of the images having features described by the composite reference image.

2. The method of claim 1 wherein the reference images are ranked and wherein calculating parameters for each reference image includes weighting the parameters based on each reference image'"'"'s rank.

3. The method of claim 1 wherein a reference image includes raster data.

4. The method of claim 1 wherein a reference image includes vector data.

5. The method of claim 1 wherein the collection includes audio objects.

6. The method of claim 5 wherein combining further comprises:

receiving one or more reference audio objects;

calculating sound parameters for each reference audio object wherein the sound parameters characterize sound features in the reference sound object that map to image parameters of at least one reference image; and

combining the sound parameters with the image parameters to produce composite reference information.

7. The method of claim 6 wherein comparing includes comparing the composite reference information to images and sound objects in a collection in order to identify one or more of the images or the sound objects having features described by the composite reference information.

8. The method of claim 1 wherein comparing further comprises calculating image parameters for the one or more images in the collection.

9. The method of claim 8 wherein comparing further comprises comparing the composite reference image to parameters of each of the one or more images in the collection.

10. The method of claim 1 further comprising:

receiving, in the computer, a selection by a user that identifies the plurality of reference images for conducting a search of an image collection, wherein the plurality of reference images are received based on the user selection;

identifying the color, texture and shape features that are common to the reference image and at least one other reference image;

wherein calculating the image parameters comprises weighting the common features more than features that are not common to the reference image and any other reference image, and wherein the composite image is generated so that it reflects the weighting;

performing the search, including the comparison of the composite reference image to the images in the collection, wherein the weighting is taken into account in the search; and

presenting a result of the search to the user.

11. A computer program product, comprising a non-transitory machine readable storage device, operable to cause one or more processors to perform operations comprising:

receiving a plurality of reference images;

calculating by a computer image parameters for each reference image wherein the image parameters characterize color, texture and shape features that are common to the reference image and at least one other reference image;

combining by the computer the calculated image parameters to generate a composite reference image; and

comparing by the computer the composite reference image to images in a collection in order to identify one or more of the images having features described by the composite reference image.

12. The program product of claim 11 wherein the reference images are ranked and wherein calculating parameters for each reference image includes weighting the parameters based on each reference image'"'"'s rank.

13. The program product of claim 11 wherein a reference image includes raster data.

14. The program product of claim 11 wherein a reference image includes vector data.

15. The program product of claim 11 wherein the collection includes audio objects.

16. The program product of claim 15 wherein combining further comprises:

receiving one or more reference audio objects;

calculating sound parameters for each reference audio object wherein the sound parameters characterize sound features in the reference sound object that map to image parameters of at least one reference image; and

combining the sound parameters with the image parameters to produce composite reference information.

17. The program product of claim 16 wherein comparing includes comparing the composite reference information to images and sound objects in a collection in order to identify one or more of the images or the sound objects having features described by the composite reference information.

18. The program product of claim 11 wherein comparing further comprises calculating image parameters for the one or more images in the collection.

19. The program product of claim 18 wherein comparing further comprises comparing the composite reference image to parameters of each of the one or more images in the collection.

20. A system comprising:

a display device;

a machine-readable storage device including a program product; and

one or more computers operable to execute the program product, interact with the display device, and perform operations comprising;

receiving a plurality of reference images;

calculating by a computer image parameters for each reference image wherein the image parameters characterize color, texture and shape features that are common to the reference image and at least one other reference image;

combining by the computer the calculated image parameters to generate a composite reference image; and

comparing by the computer the composite reference image to images in a collection in order to identify one or more of the images having features described by the composite reference image.