Method of selecting important digital images
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.
1. A method, comprising:
analyzing, via a processor of an electronic device, a plurality of images stored on a computer memory;
identifying similar images based on similarity in visual appearance, image classification similarity, event clustering, capture location similarity, capture time similarity, capture sequence order, or recurring time intervals;
combining multiple image similarity criteria to determine the sets of similar digital images forming a single image similarity metric by computing a weighted combination of the different image similarity criterion;
identifying images containing persons that are closely related to a reference individual by using automatic face recognition or by manual identification;
using the social relationship between the individuals that appear in the images as an indication of image importance;
evaluating the image quality of the digital images in each set of similar digital images based on metrics related to features such as aesthetic image quality, facial presentation, quantitative image attributes including, sharpness, image noise, image colorfulness, or image contrast;
evaluating image quality of the digital images in each of the sets of similar digital images based on metrics related to social relationships between persons included in a digital image and a reference individual; and
identifying one or more important digital images from the sets of similar digital images responsive to the determined image quality value, selecting digital images from each of the sets of similar digital images having the highest image quality value to be designated as important digital images wherein the threshold image quality level is predefined or adjusted adaptively such that the important digital images include a desired number of digital images.
2. The method of claim 1 , wherein in addition to having an image quality value that exceeds the threshold image quality level the selected important digital images are significantly different in visual appearance.
3. The method of claim 1 , further including using utilization patterns for the digital image, such as the number of times an image has been printed, viewed, shared, uploaded to social networking web sites, user-designated ratings such as, a favorites tag, and/or a high star rating as an indication of image importance.
4. The method of claim 1 , wherein the aesthetic quality of a digital image can be estimated using factors such whether the presentation of the size and location of any faces detected in the digital image follow accepted composition rules, such as the rule of thirds, vanishing points, and/or color and structure.
5. The method of claim 1 , wherein image classification similarity is determined by classifying images based on features such as scene type, such as beach, sunset, event type such as birthday, wedding, vacation, location type such as museum, playground, object type such as animal, boat, flower, and/or person identification.
6. The method of claim 1 , wherein an event cluster corresponds to a group of digital images associated with a particular event such as a birthday, holiday gathering and/or vacation.
7. The method of claim 1 , wherein capture time similarity and capture location similarity are determined for sets of digital images that are captured at capture locations within a predefined distance of each other such as determined by a global positioning system sensor and/or are captured within a predefined capture time range.
8. The method of claim 1 , wherein images falling within a specified time interval, such as the time interval corresponding to a family picnic, or images that are captured at specified recurring time intervals such as an annual events such as holidays, birthdays and summer vacations such as photos of a birthday cake on a child's birthday each year are designated to be a set of similar digital images.
9. The method of claim 1 , wherein the indications of the identified important digital images are stored, copies of the actual important digital image files are stored in a designated storage location, and/or a list of filenames for the important digital image are stored in a data storage system.
10. The method of claim 1 , wherein the indications of the identified important images are stored as metadata within the digital image itself, as an object in a database, and/or via any other storage mechanism.
11. The method of claim 1 , further including using one or more of the selected important digital images to create a photographic product such as a soft copy digital slide show, a photo album, a photo calendar or a photo collage to be presented on a digital picture frame, a computer screen background, a living room entertainment device, or a photo sharing website and/or a printed photo album, a photo collage used to fabricate photographic products such as mouse pads or coffee mugs, as a cover for a CD/DVD jewel case, and/or a photo calendar.
12. The method of claim 1 , further including sharing the selected important digital images social network or a photo-sharing website such as Facebook or Flickr and/or write protecting the selected important digital images to prevent them from being deleted.
13. The method of claim 1 , wherein the set of selected important digital images are further evaluated to assess the relative levels of importance to be used, to identify a single image or a collage of a few of the highest quality digital images for the cover of a photo album or DVD case, to identify which digital images should be emphasized such as displayed larger in a photographic product produced using the selected important digital images, and/or to identify which digital images could be used as navigational icons in a graphical user interface (GUI) for browsing the digital image collection.
14. The method of claim 1 , wherein the user can override the automatically selected important digital images by designating alternative and/or additional important digital images using Graphics User Interface.
15. The method of claim 14 , wherein the graphical use interface for manually changing the level of importance of an important digital image uses a set of radio buttons that can change the level of importance of a given important digital image by the user clicking on the radio button of the desired level of importance to set the level of importance to that value and the radio buttons can included on each of the important digital images or alternately can be shown only when selects a particular image by moving a cursor over on a particular image or by clicking on a particular image.
16. The method of claim 1 , wherein the automatic selection of important digital images is updated to preferentially select digital images based on historical user input such as selecting digital images similar to any user-selected important digital images and/or to preferentially excluding digital images similar to those which the user excluded, and/or changing to level of importance of important digital images similar to a user-selected level of importance of similar digital images.
17. The method of claim 16 , further including updating the automatic selection based on weighted composition rules based on the historical user input such as if the user chooses more face-based pictures, or pictures of particular people, or group pictures, or close-up pictures, so that the weights of those particular composition rules are adjusted accordingly.
18. The method of claim 1 , wherein a collage is created from important digital images 235 the best-in-set image is featured prominently in the center of the collage with a larger image size or other criteria can also be used, such as whether a particular collage layout requires landscape or portrait orientation images in particular locations.
19. The method of claim 1 , wherein the digital image collection is a collection of digital videos and the video frames of the digital video are each be treated as individual digital images and individual scenes within the digital video are treated as the sets of video frames and resulting selected important images are considered to be “key frames” and are used for a variety of purposes, such as they are used to form an index for a digital video summarizing the important scenes in the digital video which can then be printed or can be used to form a menu of selectable scenes that can be accessed using a remote control.