Method for reducing an amount of storage required for maintaining large-scale collection of multimedia data elements by unsupervised clustering of multimedia data elements

1. A method for reducing an amount of storage required for maintaining a large-scale collection of multimedia data elements by unsupervised clustering of multimedia data elements, comprising:

processing the multimedia data elements in the large-scale collection to generate a first cluster of multimedia data elements;

storing the first cluster in a storage unit;

repeating the generation of a new cluster from the first cluster and un-clustered multimedia data elements in the large-scale collection until a single cluster is reached;

storing the new cluster generated at each iteration in the storage unit, wherein a N-th cluster generated at the N-th iteration is stored in the storage unit, wherein the amount of storage required to store the N-th cluster is less than an amount of storage of the large-scale collection, thereby the unsupervised clustering enables reducing the storage amount required to store the multimedia data elements in the large-scale collection;

generating for each of the multimedia data elements at least one respective signature, wherein a signature is generated from multiple patches of a multimedia data element, wherein multiple patches are of random length and random position within the multimedia data element; and

performing the clustering on the respective generated signatures, thereby the created clusters include a collection of signatures respective of the multimedia data elements.

2. The method of claim 1 , wherein generating the first cluster further comprising:

matching each of the multimedia data elements to all other multimedia data elements in the large-scale collection;

determining a clustering score for each match being performed; and

clustering multimedia data elements having a clustering score above a threshold to create the first cluster.

3. The method of claim 1 , further comprising:

stopping the generation of the new cluster when it is determined that a single cluster cannot be reached.

4. The method of claim 3 , wherein generation of the N-th cluster further comprising:

clustering each of the previously generated clusters to all other previously generated clusters;

determining a clustering score for each match being performed; and

clustering multimedia data elements in clusters having a clustering score above the threshold to create the N-th cluster.

5. The method of claim 4 , wherein at each iteration for generating a new cluster, a new threshold value is utilized.

6. The method of claim 4 , wherein the clustering score is below the threshold if two clusters of the previously generated clusters include at least one overlapping multimedia data element or a multimedia data element is matched to itself.

7. The method of claim 4 , wherein the single cluster cannot be reached when no two multimedia data elements have a clustering score above the threshold or when no two previously clustered elements have a clustering score above the threshold.

8. The method of claim 1 , wherein each of the multimedia data elements is at least one of: audio, image, video, a video frame, fragment of audio, fragment of image, fragment of video, a fragment of a video frame, and an image of a signal.

9. The method of claim 8 , wherein the image of a signal is at least one of: a medical signal, a geophysical signal, a subsonic signal, a supersonic signal, an electromagnetic signal, and an infrared signal.

10. The method of claim 1 , wherein each signature is generated by a plurality of computational cores enabled to receive a plurality of multimedia data elements, each computational core having properties independent from other of the computational cores, wherein each computational core generates responsive to a multimedia data element a respective first signature element and a respective second signature element, the first signature element being a robust signature.

11. The method of claim 10 , further comprising:

setting the properties of each of the plurality of computational cores to have at least some statistical independency from other of the plurality of computational cores, the properties being set independently of each other core.

12. A non-transitory computer readable medium containing instructions that when executed on a computer perform the method of claim 1 .

13. An apparatus for reducing an amount of storage required for maintaining a large-scale collection of multimedia data elements through an unsupervised clustering of multimedia data elements, comprising:

an interface for allowing access to the large-scale collection of multimedia data elements;

at least one processing unit;

a storage unit for storing at least one cluster of multimedia data elements;

a memory coupled to the at least one processing unit and the storage unit, the memory at least a portion of which contains instructions that when executed by the at least one processing unit configure the apparatus to:

process the multimedia data elements in the large-scale collection to generate a first cluster of multimedia data elements;

store the first cluster in the storage unit;

repeat the generation of a new cluster from the first cluster and un-clustered multimedia data elements in the large-scale collection until a single cluster is reached;

store a new cluster generated at each iteration in the storage unit, wherein a N-th cluster generated at the N-th iteration is stored in the storage unit, wherein the amount of storage required to store the N-th cluster is less than an amount of storage of the large-scale collection, thereby the unsupervised clustering enables reducing the storage amount required to store the multimedia data elements in the large-scale collection;

generate for each of the multimedia data elements at least one respective signature, wherein a signature is generated from multiple patches of a multimedia data element, wherein multiple patches are of random length and random position within the multimedia data element; and

perform the clustering on the respective generated signatures, thereby the created clusters include a collection of signatures respective of the multimedia data elements.

14. The apparatus of claim 13 , wherein the processing unit is further configured to generate the first cluster by:

matching each of the multimedia data elements to all other multimedia data elements in the large-scale collection;

determining a clustering score for each match being performed; and

clustering multimedia data elements having a clustering score above a threshold to create the first cluster.

15. The apparatus of claim 14 , wherein the processing unit is configured to generate the N-th cluster by:

clustering each of the previously generated clusters to all other previously generated clusters;

determining a clustering score for each match being performed;

clustering multimedia data elements in clusters having a clustering score above the threshold to create the N-th cluster; and

storing the N-th cluster in the storage unit.

16. The apparatus of claim 15 , wherein at each iteration for generating a new cluster, a new threshold value is utilized.

17. The apparatus of claim 15 , wherein the clustering score is below the threshold if two clusters of the previously generated clusters include at least one overlapping multimedia data element or a multimedia data element is matched to itself.

18. The apparatus of claim 13 , wherein each of the multimedia data elements is at least one of: audio, image, video, a video frame, fragment of audio, fragment of image, fragment of video, a fragment of a video frame, and an image of a signal.

19. The apparatus of claim 18 , wherein the image of a signal is at least one of: a medical signal, a geophysical signal, a subsonic signal, a supersonic signal, an electromagnetic signal, and an infrared signal.

20. The apparatus of claim 13 , wherein the processing unit includes a plurality of computational cores enabled to receive a plurality of multimedia data elements, each computational core having properties independent from other of the computational cores, wherein each computational core generates responsive to a multimedia data element a respective first signature element and a respective second signature element, the first signature element being a robust signature.