Method of selecting important digital images

• US 9,858,504 B2
• Filed: 05/22/2014
• Issued: 01/02/2018
• Est. Priority Date: 09/24/2010
• Status: Active Grant

• Current Assignee: Kodak Alaris Inc (KPP (no. 2) Trustees Ltd.)
• Original Assignee: Kodak Alaris Inc (KPP (no. 2) Trustees Ltd.)
• Inventors: Hibino, Stacie L., Manico, Joseph A.
• Primary Examiner(s): YANG, WEI WEN
• Application Number:
  US14/285,163
• Publication Number:
  US 20140254945A1
• Time in Patent Office: 1,321 Days
• Field of Search: None
• CPC Class Codes: G06F 16/54 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video

Abstract

A method for selecting important digital images in a collection of digital images, comprising: analyzing the digital images in the collection of digital images to identify one or more sets of similar digital images; identifying one or more sets of similar digital images having the largest number of similar digital images; selecting one or more digital images from the identified largest sets of similar digital images to be important digital images; and storing an indication of the selected important digital image in a processor accessible memory.

Claims

1. A method for selecting important digital images in a collection of digital images, comprising:

using a processor to automatically analyze digital images in the collection of digital images to identify a plurality of sets of similar digital images;

identifying one or more subsets of the plurality of sets of similar digital images having the largest number of similar digital images;

using the processor to automatically select one digital image from each of the subsets of the plurality sets of similar digital images having the largest number of similar digital images as each being an important digital image, wherein each one digital image selected from each of the subsets is selected as being the important digital image based at least in part on an image quality level threshold value;

storing a respective indication of importance along with each one digital image selected as being the important digital image in a processor accessible memory;

automatically displaying each one digital image selected as being the important digital image on a Graphic User Interface (GUI) in a single view of the GUI, wherein automatically displaying each one digital image selected as being the important digital image comprises displaying each one digital image selected as being the important digital image arranged according to the respective indication of importance;

using the processor to evaluate the displayed each one digital image selected as being the important digital image to assess a relative level of importance with respect to each other; and

using the processor to reorder the displayed each one digital image selected as being the important digital image on the GUI according to the relative level of importance.

2. The method of claim 1, wherein the plurality of sets of similar digital images have a similar visual appearance, have a similar capture time, are captured within a specified time interval, are captured at recurring time intervals, have a similar capture location, have a similar image classification, or are captured sequentially.

3. The method of claim 1, wherein an event clustering algorithm is used to divide the collection of digital images into event clusters, and wherein the digital images within a single event cluster are designated as a set of the plurality of sets of similar digital images.

4. The method of claim 1, wherein selecting the one digital image from each of the subsets of the plurality of sets of similar digital images having the largest number of similar digital images includes:

using the processor to automatically analyze each digital image of each of the subsets of the plurality of sets of similar digital images to determine an indication of image quality as the indication of importance; and

selecting one or more other digital images as being important digital images responsive to the determined indication of image quality.

5. The method of claim 4, wherein the one digital image from each of the subsets of the plurality of sets of similar digital images having the highest image quality is selected as being an important digital image.

6. The method of claim 4, wherein the one digital image from each of the subsets of the plurality of sets of similar digital images having the highest image quality is selected as being an important digital image, except that if the digital image having the highest image quality has an image quality less than the image quality level threshold value, it is not selected as being an important digital image.

7. The method of claim 4, wherein the one digital image from each of the subsets of the plurality of sets of similar digital images having an image quality greater than the image quality level threshold value are selected as being important digital images.

8. The method of claim 7, wherein the image quality level threshold value is adaptively determined such that a specified number of important digital images are selected.

9. The method of claim 4, wherein the indication of image quality is determined responsive to computing an aesthetic image quality metric.

10. The method of claim 9, wherein the aesthetic image quality metric is responsive to the presentation of any faces detected in the one digital image from each of the subsets of the plurality of sets of similar digital images.

11. The method of claim 4, wherein the indication of image quality is determined responsive to one or more quantitative image attributes.

12. The method of claim 11, wherein the one or more quantitative image attributes includes an image sharpness attribute, an image noise attribute, an image colorfulness attribute, an image contrast attribute, or any combination thereof.

13. The method of claim 4, further including identifying one or more persons within a digital image, and wherein the indication of image quality is determined responsive to whether the identified one or more persons have a known social relationship to a reference individual.

14. The method of claim 4, wherein the indication of image quality is determined responsive to utilization patterns for the selected one digital image or is determined responsive to a user-designated rating.

15. The method of claim 1, wherein the identified largest sets of similar digital images are presented to a user on a soft copy display, together with an indication of the selected important digital images.

16. The method of claim 15, further including a user interface to enable the user to confirm or override the selection of the important digital images.

17. The method of claim 16, further including updating the automatic selection method used to select the important digital images to preferentially select digital images similar to the user-selected important digital images.

18. The method of claim 1, wherein evaluating the displayed each one digital image selected as being the important digital image comprises identifying a single image or a collage of a selected number of the highest quality digital images for the cover of a photo album or DVD case, identifying which digital images are to be emphasized or displayed larger in a photographic product produced using the selected important digital images, identifying which digital images are to be used as navigational icons in the GUI for browsing the digital image collection, clicking on a particular digital image to toggle it between being included or excluded from the set of important digital images, or using elements to visually distinguish between levels of importance.

19. The method of claim 18, wherein the GUI comprises a dashed rectangle to indicate emphasized images, a double rectangle to indicate a best-in-set image, an image size, star rating, or heart icon.

20. The method of claim 1, wherein evaluating the displayed each one digital image selected as being the important digital image comprises providing a sequence in which the important digital images are displayed is based on rank order of importance, time, themes, or a user vector of metadata or providing a set of radio buttons that can be used to change the level of importance of a given important digital image, wherein a user can click on the radio button of the desired level of importance to set the level of importance to that value.

21. The method of claim 20, wherein the set of radio buttons are included on each of the important digital images or wherein the set of radio buttons are shown only when a user selects a particular image.