USER INTERFACE FOR NAVIGATING THROUGH IMAGES

• US 20100278435A1
• Filed: 07/09/2010
• Published: 11/04/2010
• Est. Priority Date: 07/31/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Gedye, David M., Gilman, Ian A., Astort, Alfred, Aguera y Arcas, Blaise H., Dughi, Jonathan R., Ressler, Bryan
• Granted Patent: US 7,983,489 B2
• Time in Patent Office: Days
• US Class Current: 382/201
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06V 10/757 Matching configurations of points or features

Abstract

A system, method, and computer-readable media are presented for presenting similar images of a selected image in a user interface. One embodiment of the method can include identifying a selected first image and identifying a selected direction from the first image. Additionally, the method can include calculating a best neighbor metric for each of one or more other images to determine a best neighbor image in the selected direction. Furthermore, the method can include presenting the best neighbor image to a user in a user interface.

Claims

1. A method for presenting similar images of a selected image in a user interface, comprising:

identifying a first selected image;

identifying a first set of one or more keypoints in the first image;

identifying a plurality of sets of one or more keypoints in a plurality of other images;

determining a plurality of similarity metrics between the first set and each of the plurality of sets of keypoints, wherein the similarity metrics are a level of similarity between the first image and the plurality of other images;

ranking the plurality of other images based on the similarity metrics; and

presenting the plurality of other images in the ranked order around the first image.

2. The method according to claim 1, wherein the similarity metrics are distances as measured by points of differences between the first image and the plurality of other images, the distances being determined using a distance algorithm that examines the keypoints that the first image and each of the plurality of other images have in common.

3. The method according to claim 2, wherein in the distance algorithm determines the similarity metrics for each of the plurality of other images by subtracting twice the number of keypoints that the first image and a compared image of the plurality of other images have in common from the total number of keypoints found in the first image and the compared image.

4. The method according to claim 1, wherein the similarity metrics are at least one of an Euclidian distance between a camera location for the first image and each of the plurality of other images, an angular separation between vectors corresponding to the directions in which the first image and each of the plurality of other images were photographed, and the difference between the focal lengths of the first image and each of the plurality of other images, and any combination of these techniques.

5. The method according to claim 1, further comprising presenting the plurality of other images in a ranked order in at least one of concentric bands and a spiral of images around the first image, wherein the placement of the presented plurality of other images depends the similarity metric for each of the plurality of other images.

6. The method according to claim 5, wherein the plurality of other images that have a higher ranking within the ranked order are presented larger than images with a lower ranking.

7. The method according to claim 5, wherein the greater the level of similarity between the first image and each of the plurality of other images, the closer each of the plurality of images is to the first image.

8. One or more computer-storage media storing computer-executable instructions for performing a method for presenting similar images of a selected image in a user interface, the method comprising:

identifying a first selected image;

identifying a first set of one or more keypoints in the first image;

identifying a plurality of sets of one or more keypoints in a plurality of other images;

determining a plurality of similarity metrics between the first set and each of the plurality of sets of keypoints, wherein the similarity metrics are a level of similarity between the first image and the plurality of other images;

ranking the plurality of other images based on the similarity metrics; and

presenting the plurality of other images in the ranked order around the first image.

9. The media according to claim 8, wherein the similarity metrics are distances as measured by points of differences between the first image and the plurality of other images, the distances being determined using a distance algorithm that examines the keypoints that the first image and each of the plurality of other images have in common.

10. The method according to claim 9, wherein in the distance algorithm determines the similarity metrics for each of the plurality of other images by subtracting twice the number of keypoints that the first image and a compared image of the plurality of other images have in common from the total number of keypoints found in the first image and the compared image.

11. The method according to claim 8, wherein the similarity metrics are at least one of an Euclidian distance between a camera location for the first image and each of the plurality of other images, an angular separation between vectors corresponding to the directions in which the first image and each of the plurality of other images were photographed, and the difference between the focal lengths of the first image and each of the plurality of other images, and any combination of these techniques.

12. The method according to claim 8, further comprising presenting the plurality of other images in a ranked order in at least one of concentric bands and a spiral of images around the first image, wherein the placement of the presented plurality of other images depends the similarity metric for each of the plurality of other images.

13. The method according to claim 12, wherein the plurality of other images that have a higher ranking within the ranked order are presented larger than images with a lower ranking.

14. The method according to claim 12, wherein the greater the level of similarity between the first image and each of the plurality of other images, the closer each of the plurality of images is to the first image.

15. An image configuration device that executes a method for presenting similar images of a selected image in a user interface, the image configuration device comprising:

keypoint detector configured to identity a first set of one or more keypoints in a first image and a plurality of set of one or more keypoint in a plurality of other images;

keypoint analyzer configured to determine a plurality of similarity metrics between the first set and each of the plurality of sets of keypoints, wherein the similarity metrics are a level of similarity between the first image and the plurality of other images; and

user interface configured to rank the plurality of other images based on the similarity metrics and present the plurality of other images in the ranked order around the first image.

16. The method according to claim 15, wherein the similarity metrics are distances as measured by points of differences between the first image and the plurality of other images, the distances being determined using a distance algorithm that examines the keypoints that the first image and each of the plurality of other images have in common.

17. The method according to claim 16, wherein in the distance algorithm determines the similarity metrics for each of the plurality of other images by subtracting twice the number of keypoints that the first image and a compared image of the plurality of other images have in common from the total number of keypoints found in the first image and the compared image.

18. The method according to claim 15, wherein the similarity metrics are at least one of an Euclidian distance between a camera location for the first image and each of the plurality of other images, an angular separation between vectors corresponding to the directions in which the first image and each of the plurality of other images were photographed, and the difference between the focal lengths of the first image and each of the plurality of other images, and any combination of these techniques.

19. The method according to claim 15, further comprising presenting the plurality of other images in a ranked order in at least one of concentric bands and a spiral of images around the first image, wherein the placement of the presented plurality of other images depends the similarity metric for each of the plurality of other images.

20. The method according to claim 19, wherein the plurality of other images that have a higher ranking within the ranked order are presented larger than images with a lower ranking and the greater the level of similarity between the first image and each of the plurality of other images, the closer each of the plurality of images is to the first image.