Methods and systems for grouping of media based on similarities between features of the media

1. A method of managing a plurality of images, the method comprising:

providing a graphical user interface (GUI) that presents a plurality of similarity levels and allows a user to select one of the plurality of similarity levels, wherein the plurality of similarity levels correspond to a plurality of threshold distances, respectively;

identifying one of the plurality of threshold distances for clustering the plurality of images based on a degree of similarity between the plurality of images;

extracting a plurality of feature vectors corresponding to the plurality of images by identifying spatial features and global features of each of the plurality of images; and

generating a plurality of clusters each of which comprises at least two images among the plurality of images that are stored in at least one device, based on cosine distances between feature vectors corresponding to the at least two images in each of the plurality of clusters being less than the identified threshold distance.

2. The method of claim 1 , wherein the extracting of the plurality of feature vectors corresponding to the plurality of images comprises:

generating each of the plurality of feature vectors corresponding to each of the plurality of images by summarizing the spatial features and the global features of each of the plurality of images.

3. The method of claim 1 , wherein the spatial features comprise at least one of a shape and a contour of at least one object superimposed on a background of each of the plurality of images, a position of the at least one object, and a relative position of the at least one object with respect to at least one other object in each of the plurality of images.

4. The method of claim 1 , wherein the global features comprise at least one of pixel density, texture, density of color, and color distribution across each of the plurality of images.

5. The method of claim 1 , wherein the plurality of similarity levels presented in the GUI are categorized into a duplicate category, a near-duplicate category, a similar category, a near-similar category, and a dissimilar category, wherein the plurality of threshold distances correspond to the duplicate category, the near-duplicate category, the similar category, and the near-similar category, respectively.

6. The method of claim 5 , wherein, when the identified threshold distance corresponds to the duplicate category, the at least two images in each of the plurality of clusters are determined to be duplicates;

when the identified threshold distance corresponds to the near-duplicate category, the at least two images in each of the plurality of clusters are determined to be duplicates or near-duplicates;

when the identified threshold distance corresponds to the similar category, the at least two images in each of the plurality of clusters are determined to be duplicates, near-duplicates, or similar; and

when the identified threshold distance corresponds to the near-similar category, the at least two images in each of the plurality of clusters are determined to be duplicates, near-duplicates, similar, or near-similar.

7. The method of claim 1 , further comprising identifying a reference image among the plurality of images,

wherein the generating of the plurality of clusters comprises generating a first cluster comprising the reference image and at least one image of the plurality of images, and

wherein a cosine distance between one of the feature vectors that corresponds to the reference image and at least one feature vector corresponding to the at least one image in the first cluster is less than the identified threshold distance.

8. The method of claim 1 , further comprising:

identifying metadata pertaining to each of the plurality of images; and

grouping the plurality of images based on the metadata.

9. The method of claim 8 , wherein the metadata comprises at least one of a timestamp indicating a date and a time when each of the plurality of images was captured and a location where each of the plurality of images was captured.

10. An electronic device for managing a plurality of images, the electronic device comprising:

a display;

a memory storing at least one instruction; and

at least one processor configured to execute the at least one instruction to:

controlling the display to provide a graphical user interface (GUI) that presents a plurality of similarity levels and allows a user to select one of the plurality of similarity levels, wherein the plurality of similarity levels correspond to a plurality of threshold distances, respectively;

identify one of the plurality of threshold distances for clustering the plurality of images based on a degree of similarity between the plurality of images;

extract a plurality of feature vectors corresponding to the plurality of images by identifying spatial features and global features of each of the plurality of images; and

generate a plurality of clusters each of which comprises at least two images among the plurality of images that are stored in at least one device, based on cosine distances between feature vectors corresponding to the at least two images in each of the plurality of clusters being less than the identified threshold distance.

11. The electronic device of claim 10 , wherein the at least one processor is further configured to execute the at least one instruction to:

generate each of the plurality of feature vectors corresponding to each of the plurality of images by summarizing the spatial features and the global features of each of the plurality of images.

12. The electronic device of claim 10 , wherein the spatial features comprises at least one of a shape and a contour of at least one object superimposed on a background of each of the plurality of images, a position of the at least one object, and a relative position of the at least one object with respect to at least one other object in each of the plurality of images.

13. The electronic device of claim 10 , wherein the global features comprise at least one of pixel density, texture, density of color, and color distribution across each of the plurality of images.

14. The electronic device of claim 10 , wherein the plurality of similarity levels presented in the GUI are categorized into a duplicate category, a near-duplicate category, a similar category, a near-similar category, and a dissimilar category, wherein the plurality of threshold distances correspond to the duplicate category, the near-duplicate category, the similar category, and the near-similar category, respectively.

15. The electronic device of claim 14 , wherein when the identified threshold distance corresponds to the duplicate category, the at least two images in each of the plurality of clusters are determined to be duplicates;

when the identified threshold distance corresponds to the near-duplicate category, the at least two images in each of the plurality of clusters are determined to be duplicates or near-duplicates;

when the identified threshold distance corresponds to the similar category, the at least two images in each of the plurality of clusters are determined to be duplicates, near-duplicates, or similar; and

when the identified threshold distance corresponds to the near-similar category, the at least two images in each of the plurality of clusters are determined to be duplicates, near-duplicates, similar, or near-similar.

16. The electronic device of claim 10 , wherein the at least one processor is further configured to execute the at least one instruction to identify a reference image among the plurality of images, and generate a first cluster comprising the reference image and at least one image of the plurality of images, and

wherein a cosine distance between one of the feature vectors that corresponds to the reference image and at least one feature vector corresponding to the at least one image in the first cluster is less than the identified threshold distance.

17. The electronic device of claim 10 , wherein the at least one processor is further configured to execute the at least one instruction to:

identify metadata pertaining to each image of the plurality of images; and

group the plurality of images based on the metadata.

18. The electronic device of claim 17 , wherein the metadata comprises at least one of a timestamp indicating a date and a time when each of the plurality of images was captured and a location where each of the plurality of images was captured.

19. A non-transitory computer-readable storage medium storing instructions that are executable by at least one processor to perform a method of managing a plurality of images, the method comprising:

providing a graphical user interface (GUI) that presents a plurality of similarity levels and allows a user to select one of the plurality of similarity levels, wherein the plurality of similarity levels correspond to a plurality of threshold distances, respectively;

identifying one of the plurality of threshold distances for clustering the plurality of images based on a degree of similarity between the plurality of images;

extracting a plurality of feature vectors corresponding to the plurality of images by identifying the plurality of feature vectors based on spatial features and global features of each of the plurality of image; and

generating a plurality of clusters each of which comprises at least one cluster comprising at least two images among the plurality of images that are stored in at least one device, based on cosine distances between feature vectors corresponding to the at least two images in each of the plurality of clusters being less than the identified threshold distance.