System and method for creating navigable views

Patent metadata

Field	Value
Publication number	US-10115033-B2
Application number	US-201414444353-A
Country	US
Kind code	B2
Filing date	Jul 28, 2014
Priority date	Jul 30, 2013
Publication date	Oct 30, 2018
Grant date	Oct 30, 2018

Abstract

A method for creating navigable views includes receiving digital images, computing a set of feature points for each of the digital images, selecting one of the digital images as a reference image, identifying a salient region of interest in the reference image, identifying other digital images containing a region of interest similar to the salient region of interest in the reference image using the set of feature points computed for each of other digital images, designating a reference location for the salient region of interest in the reference image, aligning the other digital images to the image that contains the designated reference location, ordering the image that contains the designated reference location and the other digital images, and generating a navigable view.

First claim

The invention claimed is:

1. A method for creating navigable views using a plurality of ordered images, comprising:
receiving a plurality of digital images each including depictions of faces and at least one stationary background object distinct from the depictions of faces;
using a processor to compute a set of feature points for each of the plurality of digital images;
selecting one of the plurality of digital images as a reference image;
identifying a salient region of interest in the reference image;
using the processor to identify a set of digital images in the plurality of digital images each including a region of interest the same as the salient region of interest in the reference image using the set of feature points computed for the plurality of digital images;
designating a reference location for the salient region of interest in the reference image or in one of the set of the plurality of digital images;
using the processor to align the reference image and each of the set of the plurality of digital images with respect to the designated reference location;
ordering the reference image and each of the set of the plurality of digital images based at least in part on a time of capture of the plurality of digital images; and
generating a navigable view comprising displaying the reference image and performing a slideshow transition from the reference image to one of the set of the plurality of digital images,
wherein the salient region of interest comprises the at least one stationary background object in the reference image.

2. The method of claim 1 wherein the feature points comprise Scale-Invariant Feature Transform (SIFT) keypoints, Speeded Up Robust Feature (SURF) keypoints, Histogram of Oriented (HOG) descriptors, or Gradient Location and Orientation Histogram (GLOH) descriptors.

3. The method of claim 1 , wherein selecting one of the plurality of digital images as the reference image comprises receiving a user input as a selection of the reference image.

4. The method of claim 1 , wherein selecting one of the plurality of digital images as the reference image further includes:
using the processor to identify a set of similar images in the plurality of digital images based on the computed set of feature points; and
selecting one of the identified set of similar images as the reference image.

5. The method of claim 1 , wherein identifying the salient region of interest in the reference image comprises using the processor to identify the salient region of interest based on the computed set of feature points for the reference image.

6. The method of claim 1 , wherein identifying the salient region of interest in the reference image comprises receiving a user input as an indication of the salient region of interest.

7. The method of claim 1 , wherein aligning includes geometrically aligning the reference image and each of the set of the plurality of digital images using rotation, shifting, scaling, zooming, cropping, perspective transformation, or combinations thereof.

8. The method of claim 1 , wherein aligning includes photometrically aligning the reference image and each of the set of the plurality of digital images using color balance, tone scale adjustment, brightness enhancement, contrast enhancement, noise adjustment, or combinations thereof.

9. The method of claim 1 , wherein aligning further includes using the processor to apply filters corresponding to special effects to the set of the plurality of digital images or the reference image.

10. The method of claim 1 , wherein the reference image and the set of the plurality of digital images are ordered in chronological order, a number of people in each of the plurality of digital images, an age of each person in each of the plurality of digital images, an identity of a person in each of the plurality of digital images, or combinations thereof.

11. The method of claim 1 , wherein the navigable view comprises a slideshow presentation, a video of the ordered reference image and the set of the plurality of digital images, a panorama of the ordered reference image and the set of the plurality of digital images, an interactive presentation, an animated presentation, an interactive game, or a virtual reality environment.

12. A system for creating navigable views using a plurality of ordered images, comprising:
a memory configured to store a plurality of digital images each including depictions of faces and at least one stationary background object distinct from the depictions of faces; and
a processor configured to:
compute a set of feature points for each of the plurality of digital images;
receive a selection of one of the plurality of digital images as the reference image;
receive an identification of a salient region of interest in the reference image;
identify a set of digital images in the plurality of digital images each including a region of interest the same as the salient region of interest in the reference image using the set of feature points computed for the plurality of digital images;
designate a reference location for the salient region of interest in one of the set of the plurality of digital images;
align the reference image and each of the set of the plurality of digital images with respect to the designated reference location;
order the reference image and each of the set of the plurality of digital images based at least in part on a time of capture of the plurality of digital images;
generate a navigable view comprising displaying the reference image and performing a slideshow transition from the reference image to one of the set of the plurality of digital images; and
store the generated navigable view to the memory;

wherein the salient region of interest comprises the at least one stationary background object in the reference image.

13. The system of claim 12 , wherein the feature points comprise Scale-Invariant Feature Transform (SIFT) keypoints, Speeded Up Robust Feature (SURF) keypoints, Histogram of Oriented (HOG) descriptors, or Gradient Location and Orientation Histogram (GLOH) descriptors.

14. The system of claim 12 , wherein the processor is configured to receive a user input as a selection of the reference image.

15. The system of claim 12 , wherein the processor is configured to:
identify a set of similar images in the plurality of digital images based on the computed set of feature points; and
select one of the set of similar images as the reference image.

16. The system of claim 12 , wherein the salient region of interest in the reference image is identified based on the computed set of feature points for the reference image.

17. The system of claim 12 , wherein the processor is configured to receive a user input as an identification of the salient region of interest in the reference image.

18. The system of claim 12 , wherein the processor is configured to geometrically align the reference image and each of the set of the plurality of digital images using rotation, shifting, scaling, zooming, cropping, perspective transformation, or combinations thereof.

19. The system of claim 12 , wherein the photometrically align the reference image and each of the set of the plurality of digital images using color balance, tone scale adjustment, brightness enhancement, contrast enhancement, noise adjustment, or combinations thereof.

20. The system of claim 12 , wherein the processor is configured to apply filters corresponding to special effects to the set of the plurality of digital images or the reference

Assignees

• Kodak Alaris Inc

Inventors

• Loui Alexander C
• Manico Joseph A

Classifications

• G06V20/30 Primary

  in albums, collections or shared content, e.g. social network photos or video · CPC title

• G06F16/5854

  using shape and object relationship · CPC title

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06F17/30259

  Physics · mapped topic

• G06K9/00677

  Physics · mapped topic