System and methods thereof for generation of searchable structures respective of multimedia data content

• US 8,266,185 B2
• Filed: 10/21/2009
• Issued: 09/11/2012
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: Raichelgauz, Igal, Ordinaev, Karina, Zeevi, Yehoshua Y.
• Primary Examiner(s): Fleurantin, Jean B
• Assistant Examiner(s): Girma, Anteneh
• Application Number:
  US12/603,123
• Publication Number:
  US 20100042646A1
• Time in Patent Office: 1,056 Days
• Field of Search: None
• US Class Current: 707/803
• CPC Class Codes: G06F 16/14 Details of searching files based on file metadata
• CPC Class Codes: G06F 16/152 using file content signatures, e.g. hash values
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A system for generating concept structures respective of a plurality of multimedia data elements (MMDEs). The system comprises an attention processor (AP) for generating a plurality of items from a received MMDE of the plurality of MMDEs and determining which of the generated items that are of interest for signature generation; a signature generator (SG) for generating at least a signature responsive to at least an item of interest of the received MMDE of the plurality of MMDEs; a clustering processor (CP) for clustering a plurality of signatures received from the signature generator responsive of the plurality of MMDEs, and for creating a signature reduced cluster (SRC) of the cluster; and a concept generator (CG) for associating metadata with the SRC and matches the SRC with previously generated SRC such that SRCs that match form a concept structure comprised of a plurality of SRCs and their associated metadata.

Claims

1. A system for generating concept structures respective of a plurality of multimedia data elements (MMDEs), comprising:

an attention processor (AP) for generating a plurality of items from a received MMDE of the plurality of MMDEs and determining which of the generated items that are of interest for signature generation;

a signature generator (SG) for generating at least a signature responsive to at least an item of interest of the received MMDE of the plurality of MMDEs;

a clustering processor (CP) for clustering a plurality of signatures received from the signature generator responsive of the plurality of MMDEs, and for creating a signature reduced cluster (SRC) of the cluster, wherein the clustering processor is further configured to generate a clustering score for each signature of an MMDE of the plurality of MMDEs versus all other MMDEs of the plurality of MMDEs;

determine a size of a diagonal matrix having a size corresponding to the number of the plurality of MMDEs;

place the clustering score in a diagonal matrix in storage, one clustering score for each pair of MMDEs;

create a new cluster element for each two cluster elements in the diagonal matrix having a clustering score that exceeds a threshold; and

repeat the process at the newly created cluster element level each time using the new cluster elements generated as the plurality of cluster elements for the subsequent sequence, until a single cluster is attained or it is determined that a single cluster cannot be reached;

a concept generator (CG) for associating metadata with the SRC and matches the SRC with previously generated SRC such that SRCs that match form a concept structure comprised of a plurality of SRCs and their associated metadata; and

a tangible memory coupled to at least one of the signature generator, a clustering processor, and a concept generator.

2. The system of claim 1, wherein the AP is a patch AP (PAP) that extracts items in the form of patches from the received MMDE.

3. The system of claim 2, wherein the PAP determines which patches to provide for the signature generation based on at least one of:

the entropy level of a patch, corners identified in a patch, borders identified in a patch.

4. The system of claim 1, wherein the AP extracts items in the form of patterns from the received MMDE.

5. The system of claim 1, further comprising:

a database for storing at least one of;

MMDEs, signatures, SRCs, and concept structures; and

a network interface.

6. The system of claim 1, wherein creating the signature reduced cluster (SRC) of the cluster further comprising:

reducing the number of signatures in each cluster to a minimum that still identifies all the MMDEs associated with the cluster.

7. The system of claim 1, wherein a MMDE is selected from the group consisting of an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, a combinations thereof, and portions thereof.

8. The system of claim 7, wherein the images of signals are images selected from the group consisting of medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

9. The system of claim 1, wherein the SG comprises a plurality of computational cores, each computational core having properties statistically independent of each other computational core, each computational core generates, responsive to the received MMDE, at least a signature comprising of a first signature element and a second signature element, the first signature element being a robust signature.

10. A computer implemented method generating concept structures respective of a plurality of multimedia data elements (MMDEs) comprising:

generating a plurality of items from a received MMDE of the plurality of MMDEs;

determining the items that are of interest for signature generation;

generating at least a signature responsive to at least an item of interest of the received MMDE of the plurality of MMDEs;

clustering a plurality of signatures received from the signature generator responsive of the plurality of MMDEs;

generating a clustering score for each signature of an MMDE of the plurality of MMDEs versus all other MMDEs of the plurality of MMDEs;

determining a size of a diagonal matrix having a size corresponding to the number of the plurality of MMDEs;

placing the clustering score in a diagonal matrix in storage, one clustering score for each pair of MMDEs;

creating a new cluster element for each two cluster elements in the diagonal matrix having a clustering score that exceeds a threshold; and

repeating the process at the newly created cluster element level each time using the new cluster elements generated as the plurality of cluster elements for the subsequent sequence, until a single cluster is attained or it is determined that a single cluster cannot be reached;

reducing the number of signatures in each cluster to a minimum that still identifies all the MMDEs associated with the cluster thereby creating a signature reduced cluster (SRC) of the cluster;

associating metadata with the SRC; and

matching the SRC with previously generated SRC such that SRCs that match form a concept structure comprised of a plurality of SRCs and their associated metadata.

11. The method of claim 10, wherein generating a plurality of items further comprising:

extracting items in the form of patches from the received MMDE by a patch AP (PAP).

12. The method of claim 11, further comprising:

determining which patches to provide for the signature generation based on at least one of;

the entropy level of a patch, corners identified in a patch, borders identified in a patch.

13. The method of claim 10, wherein generating a plurality of items further comprising:

extracting items in the form of patterns from the received MMDE.

14. The method of claim 10, further comprising:

storing in a storage at least one of;

MMDEs, signatures, SRCs, and SCs.

15. The method of claim 10, further comprising:

receiving the plurality of MMDEs through a network interface.

16. The method of claim 10, further comprising:

selecting a MMDE from the group consisting of an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, a combinations thereof, and portions thereof.

17. The method of claim 16, wherein the images of signals are images selected from the group consisting of medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

18. The method of claim 10, wherein the SG comprises a plurality of computational cores, each computational core having properties statistically independent of each other computational core, each computational core generates, responsive to the received MMDE at least a signature comprising of a first signature element and a second signature element, the first signature element being a robust signature.

19. The method of claim 10, wherein an attention processor (AP) generates a plurality of items from a received MMDE of the plurality of MMDEs and further determines the items that are of interest for signature generation;

a signature generator (SG) generates at least the signature responsive to at least an item of interest of the received MMDE of the plurality of MMDEs;

a clustering processor (CP) clusters a plurality of signatures received from the signature generator responsive of the plurality of MMDEs and further reduces the number of signatures in each cluster to create a signature reduced cluster (SRC) of the cluster; and

an concept generator (CG) associates metadata with the SRC by and further matches the SRC with previously generated SRC such that SRCs that match form a concept structure comprised of a plurality of SRCs and their associated metadata.

20. The method of claim 10, is executed by computer executable code stored in computer readable medium.