Automatic curation of digital images
The disclosed subject matter relates to computer implemented methods for automatic curation of digital images. In one aspect, the method includes selecting one of every two or more duplicate digital images of a plurality of digital images. The method further includes calculating an image quality score for each of the selected digital images. The method further includes associating a ranking with each of the selected digital images based on its respective calculated image quality score.
1. A computer-implemented method for automatic curation of digital images, the method comprising:
selecting one of every two or more duplicate digital images of a plurality of digital images;
determining an image quality score for each of the selected digital images based on content and metadata of the respective digital image, the content being processed with a first processing time if an indication in the metadata corresponds to placing greater emphasis on the metadata than the content, the content being processed with a second processing time if the indication in the metadata corresponds to placing greater emphasis on the content than the metadata, the second processing time being greater than the first processing time;
associating with the each of the selected digital images, a ranking based on its respective image quality score;
generating image curation data that includes each of the selected digital images with the associated ranking; and
providing, for transmission, a digital image from the image curation data based on the associated ranking, the provided digital image being a representative digital image for the selected digital images in the image curation data.
2. The computer-implemented method of claim 1 , wherein the selecting is based on a comparison of metadata of each of the plurality of digital images.
3. The computer-implemented method of claim 1 , wherein the image quality score is based on a level of uniqueness of each of the selected digital images.
4. The computer-implemented method of claim 3 , wherein a first selected digital image comprises a first image content and a second selected digital image comprises a second image content, and the level of uniqueness of the first selected digital image is determined based on a comparison of the first image content with the second image content of the second selected digital image.
5. The computer-implemented method of claim 4 , wherein first image content comprises a first plurality of persons, and wherein the second image content comprises a second plurality of persons.
6. The computer-implemented method of claim 4 , wherein the first image content comprises a first perspective of a subject, and wherein the second image content comprises a second perspective of the subject.
7. The computer-implemented method of claim 6 , wherein the subject is a landmark.
8. The computer-implemented method of claim 6 , wherein the subject is a person.
9. The computer-implemented method of claim 1 , wherein a first selected digital image of the selected digital images depicts a person, and wherein the image quality score of the first selected digital image is based on an aspect of the person depicted in the first digital image.
10. The computer-implemented method of claim 9 , wherein the aspect is a relationship of a user with the person depicted in the first selected digital image.
11. The computer-implemented method of claim 9 , wherein the aspect is an orientation of the person's face with respect to a camera with which the first selected digital image is captured.
12. The computer-implemented method of claim 9 , wherein the aspect is an orientation of the person's eyes with respect to a camera with which the first selected digital image is captured.
13. The computer-implemented method of claim 9 , wherein the aspect is a blink status of the person's eyes.
14. The computer-implemented method of claim 9 , wherein the aspect is a smile status of the person.
15. The computer-implemented method of claim 1 , further comprising:
deselecting a first digital image of the selected digital images based on the respective image quality score of the first digital image; and
providing for display, an explanation of the deselecting of the first digital image.
16. The computer-implemented method of claim 15 , further comprising:
reselecting, based on a received indication of a user-selection, the first digital image.
17. A system for automatic curation of digital images, the system comprising:
a memory comprising instructions for automatic curation of digital images; and a processor configured to execute the instructions to:
calculate an image quality score for a digital image, wherein the calculation is based on each of an image content of the digital image and metadata of the digital image, the image content being processed with a first processing time if an indication in the metadata corresponds to placing greater emphasis on the metadata than the image content, the image content being processed with a second processing time if the indication in the metadata corresponds to placing greater emphasis on the image content than the metadata, the second processing time being greater than the first processing time;
associate with the digital image, a ranking based on the calculated image quality score;
generate image curation data that includes each of the selected digital images with the associated ranking; and
provide, for transmission, a digital image from the image curation data based on the associated ranking, the provided digital image being a representative digital image for the selected digital images in the image curation data.
18. A non-transitory computer-readable medium encoded with executable instructions that, when executed by a processor, cause the processor to perform a method comprising:
selecting one of every two or more duplicate digital images of a plurality of digital images;
determining an image quality score for each of the selected digital images based on content and metadata of the respective digital image, the content being processed with a first processing time if an indication in the metadata corresponds to placing greater emphasis on the metadata than the content, the content being processed with a second processing time if the indication in the metadata corresponds to placing greater emphasis on the content than the metadata, the second processing time being greater than the first processing time;
associating with the each of the selected digital images, a ranking based on its respective image quality score;
generating image curation data that includes each of the selected digital images with the associated ranking; and
providing, for transmission, a digital image from the image curation data based on the associated ranking, the provided digital image being a representative digital image for the selected digital images in the image curation data.