Manufacture of image inventories

• US 10,289,915 B1
• Filed: 06/05/2018
• Issued: 05/14/2019
• Est. Priority Date: 06/05/2018
• Status: Active Grant

• Current Assignee: Eight Plus Ventures, LLC
• Original Assignee: Eight Plus Ventures, LLC
• Inventors: Bertsch, Christoph, Lake, Rodney, Sturgeon, Douglas, Sziklai, Anthony
• Primary Examiner(s): Edwards, Linglan E
• Application Number:
  US16/000,410
• Time in Patent Office: 343 Days
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/71 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06T 1/0021 Image watermarking
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: H04L 2209/608 Watermarking
• CPC Class Codes: H04L 9/0643 Hash functions, e.g. MD5, SHA, HMAC or f9 MAC
• CPC Class Codes: H04L 9/3239 involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD
• CPC Class Codes: H04L 9/50 using hash chains, e.g. blockchains or hash trees

Abstract

There are disclosed methods and apparatus for manufacture of image inventories. A frame slicing and packaging machine assigns metadata to each frame of a digital video work. It then detects objects in each frame'"'"'s image, recognizes the objects and assigns metadata to the objects. The machine then generates a cryptographic hash of the frame'"'"'s image. Lastly, the machine writes the hash to a node of a transaction processing network.

Claims

1. An apparatus comprising a non-volatile machine readable medium storing a program having instructions which when executed by a processor will cause the processor to manufacture an inventory of image products from frames of a digital video work, each frame comprising a still image in sequence in the work, the digital video work including audio which corresponds to objects in the still images in the digital video work from which the audio is produced, the instructions of the program for:

assigning metadata to each frame of the digital video work, the frame metadata including an identification of the work, provenance of the work, and an identification of the frame within the work;

detecting objects in each frame'"'"'s image;

recognizing the objects;

assigning metadata to the objects, including location in the frame and recognition of the object, the object metadata further linking spoken lines and sound in audio from the digital video work to the corresponding object in the frame'"'"'s image which produces the spoken lines and sound;

for each frame, generating a cryptographic hash of the frame'"'"'s image, the frame metadata, and the object metadata;

writing the hash to a node of a transaction processing network.

2. The apparatus of claim 1 further comprising extracting from a physical medium a sequence of analog form images and converting them to digital form.

3. The apparatus of claim 1 wherein the digital video work is a whole movie.

4. The apparatus of claim 1 wherein the digital video work is a portion of a movie.

5. The apparatus of claim 1 wherein at least one recognized object is at least one of a person, an animal and a good.

6. The apparatus of claim 5 wherein metadata of a person comprises an actor'"'"'s name.

7. The apparatus of claim 1 wherein the frame metadata includes color compositions within the frame.

8. The apparatus of claim 1 wherein the frame metadata includes tags describing the frame'"'"'s image, a geographic location where the frame'"'"'s image was filmed, a geographic location of where the frame'"'"'s image is represented to be in the work.

9. The apparatus of claim 1 wherein the frame includes audio, and the instructions are further for detecting objects in the frame'"'"'s audio.

10. The apparatus of claim 9, wherein the metadata for audio objects includes spoken lines and sounds.

11. The apparatus of claim 1 wherein the transaction processing network is a blockchain ledger.

12. The apparatus of claim 1 wherein the hash is an individual file, such that there is one file produced from each frame of the digital video work.

13. The apparatus of claim 1 further comprising adding a watermark to the hash before it is written to the node.

14. The apparatus of claim 1 wherein at least some of the metadata links objects across frames.

15. The apparatus of claim 1 wherein at least some of the metadata links objects across frames.

16. A process for manufacturing an inventory of image products from frames of a digital video work, each frame comprising a still image in sequence in the work, the digital video work including audio which corresponds to objects in the still images in the digital video work from which the audio is produced, the process comprising:

assigning metadata to each frame of the digital video work, the frame metadata including an identification of the work, provenance of the work, and an identification of the frame within the work;

detecting objects in each frame'"'"'s image;

recognizing the objects;

assigning metadata to the objects, including location in the frame and recognition of the object, the object metadata further linking spoken lines and sound in audio from the digital video work to the corresponding object in the frame'"'"'s image;

for each frame, generating a cryptographic hash of the frame'"'"'s image, the frame metadata, and the object metadata;

writing the hash to a node of a transaction processing network.

17. The process of claim 16 further comprising extracting from a physical medium a sequence of analog form images and converting them to digital form.

18. The process of claim 16 wherein the digital video work is a whole movie.

19. The process of claim 16 wherein the digital video work is a portion of a movie.

20. The process of claim 16 wherein at least one recognized object is at least one of a person, an animal and a good.

21. The process of claim 20 wherein metadata of a person comprises an actor'"'"'s name.

22. The process of claim 16 wherein the frame metadata includes color compositions within the frame.

23. The process of claim 16 wherein the frame metadata includes tags describing the frame'"'"'s image, a geographic location where the frame'"'"'s image was filmed, a geographic location of where the frame'"'"'s image is represented to be in the work.

24. The process of claim 16 wherein the frame includes audio, and the instructions are further for detecting objects in the frame'"'"'s audio.

25. The process of claim 24, wherein the metadata for audio objects includes spoken lines and sounds.

26. The process of claim 16 wherein the transaction processing network is a blockchain ledger.

27. The process of claim 16 wherein the hash is an individual file, such that there is one file produced from each frame of the digital video work.

28. The process of claim 16 further comprising adding a watermark to the hash before it is written to the node.