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;
separating, via the processor, the plurality of images into subsets of related images, wherein the related images are determined using a visual similarity algorithm;
identifying all largest subsets of related images from within the subsets of related images, wherein the largest subsets include a number of related images greater than a pre-defined threshold;
determining, via the processor, an image quality of each image in the largest subsets of related images;
assigning, via the processor, an image quality value to each image in the largest subsets of related images based in part on the determined image quality of each image;
designating, via the processor, an important image from each of the largest subsets of related images, each important image having been assigned the highest image quality value of any image in its largest subset of related images;
integrating the important images into a photographic product; and
displaying a rendering of the photographic product on a display of the electronic device.
2. The method of claim 1 , wherein determining the image quality of each image in the largest subsets of related images comprises determining a technical image quality of each image.
3. The method of claim 2 , wherein determining the technical image quality of each image comprises determining a quantitative image attribute of each image, wherein the quantitative image attribute is selected from the group consisting of: sharpness, an image noise, an image colorfulness, and an image contrast.
4. The method of claim 1 , wherein determining the image quality of each image in the largest subsets of related images comprises determining a social relationship between persons appearing in respective images of the first subset.
5. The method of claim 4 , wherein designating an important image from each of the largest subsets of related images comprises:
selecting a reference person from the plurality of stored images; and
determining an identity of each of the persons appearing in the respective images of the largest subsets of related images.
6. The method of claim 5 , wherein designating an important image from each of the largest subsets of related images comprises:
determining a level of the social relationship between the persons and the reference person based at least in part on the determined identity of each of the persons appearing in the respective images of the largest subsets of related images; and
assigning a level of importance to each image of the respective images of the largest subsets of related images based at least in part on the level of the social relationship.
7. The method of claim 1 , wherein assigning the image quality value to each image in the largest subsets of related images comprises assigning an image quality value based at least in part on a comparison of the image quality of each image of the largest subsets to a configurable image quality threshold.
8. An electronic device, comprising:
a processor configured to:
analyze a plurality of stored images;
separate the plurality of stored images into subsets of related images, wherein the related images are determined using a visual similarity algorithm;
identify all largest subsets of related images from within the subsets of related images, wherein the largest subsets include a number of related images greater than a pre-defined threshold;
determine an image quality of each image in the largest subsets of related images;
assign an image quality value to each image in the largest subsets of related images based at least in part on the determined image quality of each image;
designate an important image from each of the largest subsets of related images, wherein each important image is based at least in part on the image quality value;
integrate the important images into a photographic product; and
cause a rendering of the photographic product to be displayed on a display of the electronic device.
9. The electronic device of claim 8 , further comprising an electronic display, wherein the processor is configured to cause the electronic display to display the important images from each of the largest subsets of related images, along with indications of their importance.
10. The electronic device of claim 9 , wherein the processor is configured to cause the electronic display to display the largest subsets of related images along with the important images from the largest subsets of related images.
11. A non-transitory computer-readable medium having computer executable code stored thereon, the code comprising instructions to cause:
a processor of an electronic device to analyze a set of stored images and identify subsets of related images, wherein the related images are determined using a visual similarity algorithm;
the processor to identify all largest subsets of related images from within the subsets of related images, wherein the largest subsets of related images include a number of related images greater than a pre-defined threshold;
the processor to determine an image quality of each image in the largest subsets of related images;
the processor to assign an image quality value to each image in the largest subsets of related images based on the determined image quality of each image;
the processor to designate an important image from each of the largest subsets of related images based on the assigned image quality value;
the processor to integrate the important images into a photographic product; and
an electronic display to display a rendering of the photographic product.
12. The non-transitory computer-readable medium of claim 11 , wherein the code comprises instructions to cause the processor to analyze the largest subsets of related images and determine a social relationship between persons appearing in respective images of the largest subsets of related images.
13. The non-transitory computer-readable medium of claim 12 , wherein the code comprises instructions to cause:
the processor to select a reference person from the set of stored images; and
the processor to determine an identity of each person appearing in the respective images of the largest subsets of related images.
14. The non-transitory computer-readable medium of claim 13 , wherein the code comprises instructions to cause:
the processor to determine a level of the social relationship between the persons appearing in the respective images of the largest subsets of related images and the reference person; and
the processor to assign a level of importance to each image in the largest subsets of related images based at least in part on the level of the social relationship.
15. The non-transitory computer-readable medium of claim 11 , wherein the code comprises instructions to cause the processor to assign an image quality value to each image in the largest subsets of related images based at least in part on a comparison of the image quality and a configurable image quality threshold.
16. The non-transitory computer-readable medium of claim 11 , wherein the code comprises instructions to cause the processor to cause the important images from the largest subsets of related images along with an indication of their importance to be displayed on an electronic display.