CONCEPT-STRUCTURED IMAGE SEARCH

• US 20130151510A1
• Filed: 02/06/2013
• Published: 06/13/2013
• Est. Priority Date: 09/23/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Hua, Xian-Sheng, Wang, Jingdong, Xu, Hao
• Granted Patent: US 8,706,740 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

The concept-structured image search technique described herein pertains to a technique for enabling a user to indicate their semantic intention and then retrieve and rank images from a database or other image set according to this intention. The concept-structured image search technique described herein includes a new interface for image search. With this interface, a user can freely type several key textual words in arbitrary positions on a blank image, and also describe a region for each keyword that indicates its influence scope, which is called concept structure herein. The concept-structured image search technique will return and rank images that are in accordance with the concept structure indicated by the user. One embodiment of the technique can be used to create a synthesized image without actually using the synthesized image to perform a search of an image set.

Claims

1. In a computer system comprising a display and a user interface data entry device, a process for finding an image in a set of images, comprising:

displaying on the display a window for entering a concept-structured query comprising a concept-structured layout of an image to be found in the set of images;

a user inputting a concept-structured query into the window for entering the concept-structured layout using the user interface data entry device; and

outputting on the display a ranked list of images of the set of images based on similarity of the images with the concept-structured layout.

2. The system of claim 1 wherein a user inputs the concept-structured query by typing keywords in the window for entering the concept-structured layout at a location where the concept of the keyword is sought.

3. The system of claim 2 further comprising associating ellipses with each of the keywords to specify the scope and location of the concept associated with the keyword in an image.

4. The system of claim 3 wherein the user can edit the direction and size of the ellipses to alter the scope and location of the concept associated with the keyword in an image.

5. The system of claim 1, further comprising:

synthesizing an image from representative images that represent the keywords entered; and

using the synthesized image to find an image in the set of images that is similar to the concept-structured layout.

6. The system of claim 5, further comprising using the synthesized image to find an image similar to the concept-structured layout in a new set of images.

7. A process for finding an image in a set of images, comprising:

displaying on a display a window for entering a concept-structured query comprising a concept-structured layout of an image to be found in the set of images;

a user inputting a concept-structured query into the window for entering the concept-structured layout using a user interface data entry device; and

outputting on the display a ranked list of images of the set of images based on similarity of the images with the concept-structured layout.

8. The process of claim 7 wherein a user inputs the concept-structured query by typing keywords in the window for entering the concept-structured layout at a location where the concept of the keyword is sought.

9. The process of claim 8 further comprising associating ellipses with each of the keywords to specify the scope and location of the concept associated with the keyword in an image.

10. The process of claim 9 wherein the user can edit the direction and size of the ellipses to alter the scope and location of the concept associated with the keyword in an image.

11. The process of claim 7, further comprising:

synthesizing an image from representative images that represent the keywords entered; and

using the synthesized image to find an image in the set of images that is similar to the concept-structured layout.

12. The process of claim 11, further comprising using the synthesized image to find an image similar to the concept-structured layout in a new set of images.