Object tag metadata and image search

• US 9,008,433 B2
• Filed: 02/08/2012
• Issued: 04/14/2015
• Est. Priority Date: 02/08/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fork, Michael J., Hamilton, Rick A. II, Paterson, Kevin G., Seaman, James W.
• Primary Examiner(s): Chang, Jon
• Assistant Examiner(s): Mistry, Oneal R
• Application Number:
  US13/368,775
• Publication Number:
  US 20130202216A1
• Time in Patent Office: 1,161 Days
• Field of Search: None
• US Class Current: 382/190
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information

Abstract

Techniques are disclosed for ordering images. The technique includes receiving a request, the request including keywords and parameters specifying desired image characteristics. Further, the technique includes identifying a set of images responsive to the request based on a match of the keywords to tags associated with objects depicted in the set of images. Finally, the technique includes determining an ordering of the identified set of images by comparing the received parameters with metadata fields associated with respective tags of the objects and returning an indication of the set of images and the determined ordering of the images.

Claims

1. A non-transitory computer-readable storage medium storing a program, which, when executed by a processor performs an operation in response to an image search request, the operation comprising:

receiving a request which includes one or more keywords and one or more metadata parameters specifying desired image characteristics;

identifying, via one or more processors, a set of images, wherein the identified set of images is responsive to the request based on at least a match of the keywords to image tags, wherein each image tag is associated with one of a plurality of objects which is depicted in one of the images from the set of images;

determining an ordering of the identified set of images by comparing the received metadata parameters with corresponding tag metadata fields, each tag metadata field being distinct from and associated with one of the image tags; and

returning an indication of the set of images and the determined ordering of the images,

wherein each tag metadata field has a numerical value, the numerical value being determined as a relative value of a given image characteristic of one of the objects as depicted in one of the images when compared to the given image characteristic of the one of the objects as depicted in a plurality of images of an image repository, and

wherein determining the ordering of the identified set of images comprises;

comparing the received parameters with the corresponding tag metadata fields to determine whether predefined threshold values are met;

for each of the predefined threshold values that is met, increasing a weight value for the image tag to which the corresponding tag metadata field is associated; and

ordering the set of images based on at least the weight values for the image tags associated with the images in the set of images.

2. The non-transitory computer-readable storage medium of claim 1, wherein each tag metadata field represents an image characteristic of one of the plurality of objects as the object appears within a respective image relative to the image characteristic of the object as the object appears within images of an image repository sharing the image tag to which the respective tag metadata field is associated.

3. The non-transitory computer-readable storage medium of claim 1, wherein a first one of the tag metadata fields represents a relative size of one of the objects.

4. The non-transitory computer-readable storage medium of claim 1, wherein a first one of the tag metadata fields represents a relative focus of one of the objects.

5. The non-transitory computer-readable storage medium of claim 1, wherein a first one of the tag metadata fields represents a relative contrast of one of the objects.

6. The non-transitory computer-readable storage medium of claim 1, wherein a first one of the tag metadata fields represents a relative isolation of one of the objects.

7. The non-transitory computer-readable storage medium of claim 1, wherein comparing the received metadata parameters with tag metadata fields includes determining whether a value of a tag metadata field exceeds a predefined threshold value.

9. The non-transitory computer-readable storage medium of claim 1, wherein the set of images includes at least one dynamic image or a video sequence itself comprising a plurality of images.

8. A system, comprising:

a processor; and

a memory, wherein the memory includes an application program configured to perform an operation in response to a search request, the operation comprising;

receiving a request which includes one or more keywords and one or more metadata parameters specifying desired image characteristics,

identifying, via one or more processors, a set of images responsive to the request based on at least a match of the keywords to image tags, wherein each image tag is associated with one of a plurality of objects which is depicted in one of the images from the set of images,

determining an ordering of the identified set of images by comparing the received metadata parameters with corresponding tag metadata fields, each tag metadata field being distinct from and associated with one of the image tags, and

returning an indication of the set of images and the determined ordering of the images,

wherein each tag metadata field has a numerical value, the numerical value being determined as a relative value of a given image characteristic of one of the objects as depicted in one of the images when compared to the given image characteristic of the one of the objects as depicted in a plurality of images of an image repository, and

wherein determining the ordering of the identified set of images comprises;

comparing the received parameters with the corresponding tag metadata fields to determine whether predefined threshold values are met;

for each of the predefined threshold values that is met, increasing a weight value for the image tag to which the corresponding tag metadata field is associated; and

ordering the set of images based on at least the weight values for the image tags associated with the images in the set of images.