Metadata record generation

• US 8,924,423 B2
• Filed: 07/23/2013
• Issued: 12/30/2014
• Est. Priority Date: 10/09/2009
• Status: Active Grant

• Current Assignee: Soundmouse Limited
• Original Assignee: Adelphoi Ltd.
• Inventors: Hodgkinson, Charles, Zavieh, Kirk
• Primary Examiner(s): Woo, Isaac M
• Application Number:
  US13/948,874
• Publication Number:
  US 20130311512A1
• Time in Patent Office: 525 Days
• Field of Search: 707600-899
• US Class Current: 707/791
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/483 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/489 using time information
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content

Abstract

A computer implemented method and system provide for automatic selection and extraction of metadata and media content from projects in a craft tool. Automated identification, classification and management of such metadata and content is provided using including techniques such as pattern recognition for audio and visual content. The automatic tracking and centralized storage of metadata and content for compliance purposes can be facilitated, and can enable querying of organized metadata stored in a central database. In an example, metadata and media content are extracted automatically from a project in a craft tool at a client system and are forwarded to a host system for the creation of a cue sheet including timings for media files from timing metadata in a project file to create the timings on the cue sheet.

Claims

1. A computer-implemented method of analyzing a media project defined by a craft tool, the method comprising:

receiving a file for the media project defined by the craft tool, wherein the craft tool is a computer-implemented tool for audio and/or visual editing, the media project includes a plurality of media items in at least one of a plurality of tracks and project bins, and the received file comprises media content extracted from the plurality of media items;

comparing a representation generated from media content extracted from a particular one of the plurality of media items to reference representations in a database of reference items to identify a match, wherein;

the reference items in the reference database include associated reference metadata,

the representation generated from the media content extracted from the particular media item of the media project is a fingerprint generated from the media content extracted from the particular media item of the media project, and

the corresponding reference item comprises a representation in the form of a fingerprint generated from a reference work and associated metadata identifying the reference work; and

in response to identifying a corresponding reference item in the reference database for which the representation generated from the content extracted from the particular media item matches the reference representation for the corresponding reference item, using the associated reference metadata to identify the media content extracted from the particular media item.

2. The method of claim 1, wherein the comparing comprises performing pattern recognition between the representation generated from the media content extracted from the particular one of the plurality of media items to reference representations in the database of reference items to identify the match.

3. The method of claim 1, wherein said media content extracted from the particular one of the plurality of media items is at least one of video, image, text or audio media, and wherein the representation of said media content from the particular one of the plurality of media items is a representation of said at least one of video, image, text or audio media.

4. The method of claim 3, wherein the representation of said media content from the particular media item is a representation of at least one of faces, images, voices, moods, and product placement opportunities from said video, image, text or audio media.

5. The method of claim 1, wherein:

the fingerprint generated from the media content extracted from the particular media item of the media project is a Fourier transform generated from the media content extracted from the particular media item of the media project; and

the corresponding reference item comprises a representation in the form of a Fourier transform generated from the reference work and associated metadata identifying the reference work.

6. The method of claim 1, wherein the received file for the media project defined by the craft tool further includes the representation generated from the media content extracted from the particular media item of the media project.

7. The method of claim 1, wherein the received file for the media project defined by the craft tool further includes metadata extracted from the media project defined by the craft tool.

8. The method of claim 7, further comprising:

adding a reference item to the reference database when no item in the reference database is identified that has a reference representation that matches the representation generated from the content extracted from the particular media item, the added reference item including the representation generated from the media content extracted from the particular media item and metadata extracted from the received file and associated with the media content extracted from the particular media item.

9. The method of claim 1, further comprising outputting a metadata record file comprising the associated reference metadata to identify the media content extracted from the particular media item of the media project.

10. The method of claim 9, wherein the metadata record file comprises a cue sheet including metadata identifying a rights holder in respect of the media content.

11. The method of claim 9, wherein the metadata record file includes metadata identifying at least one of:

a face, an image, a voice, a mood, and a product placement opportunity.

12. A system comprising at least one computer server, the system configured to:

receive a file for a media project defined by a craft tool, wherein the craft tool is a tool for audio and/or visual editing implemented by a client system, the media project includes a plurality of media items in at least one of a plurality of tracks and project bins, and the received file comprises media content extracted from media items of the media project;

compare a representation generated from media content extracted from a particular one of the plurality of media items of the media project to reference representations in a database of reference items to identify a match, wherein;

the reference items in the reference database comprise reference representations and associated reference metadata,

the representation generated from the media content extracted from the particular media item of the media project is a fingerprint generated from the media content extracted from the particular media item of the media project, and

the corresponding reference item comprises a representation in the form of a fingerprint generated from a reference work and associated metadata identifying the reference work; and

use, in response to identifying a corresponding item in the reference database for which the representation generated from the content extracted from the particular media item matches the reference representation in the corresponding item in the reference database, the associated reference metadata to identify the media content extracted from the particular media item of the media project.

13. The system of claim 12, further configured to compare a representation generated from media content extracted from the particular media item of the media project to reference representations in a database of reference items to identify a match by performing pattern recognition between the representation generated from the media content extracted from the particular media item of the media project to reference representations in the database of reference items to identify a match.

14. The system of claim 12, wherein the received file for the media project defined by the craft tool further includes metadata extracted from the received file.

15. The system of claim 12, further configured to add a reference item to the reference database when no item in the reference database is identified that has a reference representation that matches the representation generated from the content extracted from the particular media item, the added reference item including the representation generated from the media content extracted from the particular media item and metadata extracted from the project and associated with said media content extracted from the particular media item.

16. The system of claim 12, wherein the corresponding reference item comprises a representation in the form of a fingerprint generated from the corresponding reference work and associated metadata identifying the reference work.

17. The system of claim 12, wherein the corresponding reference item comprises a representation in the form of a Fourier transform generated from the corresponding reference work and associated metadata identifying the reference work.

18. The system of claim 12, wherein the received file for the media project defined by the craft tool further includes at least one of the representation generated from the media content extracted from the particular media item of the media project, or metadata extracted from the media project defined by the craft tool.

19. The system of claim 12, further configured to output a metadata record file comprising the associated reference metadata to identify the media content extracted from the particular media item of the media project.

20. A system comprising at least one computer server, the system configured to:

receive a file for a media project defined by a craft tool, wherein the craft tool is a tool for audio and/or visual editing implemented by a client system, the media project includes a plurality of media items in at least one of a plurality of tracks and project bins, and the received file comprises media content extracted from media items of the media project;

compare a representation generated from media content extracted from a particular one of the plurality of media items of the media project to reference representations in a database of reference items to identify a match, wherein the reference items in the reference database comprise reference representations and associated reference metadata; and

use, in response to identifying a corresponding item in the reference database for which the representation generated from the content extracted from the particular media item matches the reference representation in the corresponding item in the reference database, the associated reference metadata to identify the media content extracted from the particular media item of the media project;

wherein the system is further configured to add a reference item to the reference database when no item in the reference database is identified that has a reference representation that matches the representation generated from the content extracted from the particular media item, the added reference item including the representation generated from the media content extracted from the particular media item and metadata extracted from the project and associated with said media content extracted from the particular media item.