Searching images with extracted objects

• US 7,716,157 B1
• Filed: 01/26/2006
• Issued: 05/11/2010
• Est. Priority Date: 01/26/2006
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Heileson, Jeffery Scott, Schendel, Claire, Bourdev, Lubomir
• Primary Examiner(s): Vy; Hung T
• Assistant Examiner(s): Ho; Binh V
• Application Number:
  US11/341,247
• Time in Patent Office: 1,566 Days
• Field of Search: 707/2
• US Class Current: 382/118
• 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 16/5838 using colour
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing

Abstract

Presenting a subset is disclosed. Information associated with a set of one or more objects is obtained, where the set of one or more objects have been detected from a collection of one or more images. Object search criteria is obtained. A subset of the collection is determined based at least in part on the object search criteria. The subset is presented.

Claims

1. A method comprising:

obtaining information associated with a set of one or more objects, wherein;

the set of one or more objects having been detected from a collection of one or more images using a face detection process; and

the information associated with the set of objects is output by the face detection process and includes values for a set of one or more parameters;

presenting a search interface via which a reference image having one or more reference face objects is obtained;

obtaining, via the search interface, object search criteria that includes the reference image;

determining, after the face detection process has been performed, a subset of the collection of one or more images that match the reference image based at least in part on a number of reference face objects in the reference image and a placement of the reference face objects within the reference image, wherein the placement of the reference face objects within the reference image is based at least in part on a calculated coordinates of the face objects within the reference image or on a the calculated coordinates of the face objects relative to the calculated coordinates of one or more other objects within the reference image, wherein the object search criteria further includes and determining is further based at least in part on one of the following;

a tag assigned to at least one of the reference face objects, information associated with orientation, information associated with an accessory, or information associated with a tag assigned to an image, wherein determining is performed by a processor; and

presenting the subset.

2. A method as recited in claim 1, wherein detecting includes an automatic detection process.

3. A method as recited in claim 1, wherein the information is obtained from a database.

4. A method as recited in claim 1, wherein determining is further based at least in part on the size of the reference face objects in the reference image.

5. A method as recited in claim 1, wherein a confidence level is associated with the object search criteria and identifying the subset includes considering the confidence level.

6. A method as recited in claim 1, wherein the reference image includes an image constructed by a user and presenting the search interface includes presenting one or more interface controls configured to add a new face object to the reference image, adjust the position of a selected face object in the reference image, and/or adjust the size of a selected face object in the reference image.

7. A method as recited in claim 1, wherein the reference image includes an image selected by a user and presenting the search interface includes presenting one or more interface controls configured to receive a selection of an image as the reference image.

8. A method as recited in claim 1, wherein determining includes using a margin.

9. A method as recited in claim 1, wherein the collection is specified by a user.

10. A method as recited in claim 1, further including calculating a degree to which the object search criteria is satisfied.

11. A method as recited in claim 1, wherein presenting includes displaying one or more images included in the subset.

12. A method as recited in claim 1, wherein the subset is presented according to a degree to which the object search criteria is satisfied.

13. A system comprising:

a processor; and

a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to;

obtain information associated with a set of one or more objects, wherein;

the set of one or more objects having been detected from a collection of one or more images using a face detection process; and

the information associated with the set of objects is output by the face detection process and includes values for a set of one or more parameters;

present a search interface via which a reference image having one or more reference face objects is obtained;

obtain, via the search interface, object search criteria that includes the reference image;

determine, after the face detection process has been performed, a subset of the collection of one or more images that match the reference image based at least in part on a number of reference face objects in the reference image and a placement of the reference face objects within the reference image;

wherein the placement of the reference face objects within the reference image is based at least in part on calculated coordinates of the face objects within the reference image or on calculated coordinates of the face objects relative to calculated coordinates of one or more other objects within the reference image, wherein the object search criteria further includes and determining is further based at least in part on one of the following;

a tag assigned to at least one of the reference face objects, information associated with orientation, information associated with an accessory, or information associated with a tag assigned to an image; and

present the subset.

14. A system as recited in claim 13, wherein detecting includes an automatic detection process.

18. A system as recited in claim 13, wherein the reference image includes an image constructed by a user and presenting the search interface includes presenting one or more interface controls configured to add a new face object to the reference image, adjust the position of a selected face object in the reference image, and/or adjust the size of a selected face object in the reference image.

19. A system as recited in claim 13, wherein the reference image is an image selected by a user and the instructions for presenting the search interface include instructions for presenting one or more interface controls configured to receive a selection of an image as the reference image.

22. A system as recited in claim 13, wherein determining is further based at least in part on the size of the reference face objects in the reference image.

15. A computer program product being embodied in a computer readable storage medium and comprising computer instructions for:

obtaining information associated with a set of one or more objects, wherein;

the set of one or more objects having been detected from a collection of one or more images using a face detection process; and

the information associated with the set of objects is output by the face detection process and includes values for a set of one or more parameters;

presenting a search interface via which a reference image having one or more reference face objects is obtained;

obtaining, via the search interface, object search criteria that includes the reference image;

determining, after the face detection process has been performed, a subset of the collection of one or more images that match the reference image based at least in part on a number of reference face objects in the reference image and a placement of the reference face objects within the reference image;

wherein the placement of the reference face objects within the reference image is based at least in part on calculated coordinates of the face objects within the reference image or on calculated coordinates of the face objects relative to calculated coordinates of one or more other objects within the reference image, wherein the object search criteria further includes and determining is further based at least in part on one of the following;

a tag assigned to at least one of the reference face objects, information associated with orientation, information associated with an accessory, or information associated with a tag assigned to an image; and

presenting the subset.

16. A computer program product as recited in claim 15, wherein the object search criteria further includes and determining is further based at least in part on information associated with a tag assigned to an object.

17. A computer program product as recited in claim 15, the computer program product further comprising computer instructions for calculating a degree to which the object search criteria is satisfied.

20. A computer program product as recited in claim 15, wherein the reference image includes an image constructed by a user and presenting the search interface includes presenting one or more interface controls configured to add a new face object to the reference image, adjust the position of a selected face object in the reference image, and/or adjust the size of a selected face object in the reference image.

21. A computer program product as recited in claim 15, wherein the reference image is an image selected by a user and the computer instructions for presenting the search interface include computer instructions for presenting one or more interface controls configured to receive a selection of an image as the reference image.

23. A computer program product as recited in claim 15, wherein determining is further based at least in part on the size of the reference face objects in the reference image.