Optimization processes for compressing media content

• US 10,303,925 B2
• Filed: 06/24/2016
• Issued: 05/28/2019
• Est. Priority Date: 06/24/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Hart, Bryan, Zulkower, Valentin
• Primary Examiner(s): Alavi, Amir
• Application Number:
  US15/192,835
• Publication Number:
  US 20180268567A1
• Time in Patent Office: 1,068 Days
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/432 Query formulation
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/44 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/784 the detected or recognised objects being people
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/0489 using dedicated keyboard keys or combinations thereof
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 13/80 2D [Two Dimensional] animation, e.g. using sprites
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2210/12 : Bounding box
• CPC Class Codes: G06T 7/285 : using a sequence of stereo image pairs
• CPC Class Codes: G06T 7/90 : Determination of colour characteristics
• CPC Class Codes: G06T 9/00 : Image coding bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00
• CPC Class Codes: G06V 40/162 : using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/171 : Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: H04L 69/04 : Protocols for data compression, e.g. ROHC
• CPC Class Codes: H04N 19/154 : Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion use of rate-distortion criteria H04N19/147
• CPC Class Codes: H04N 19/172 : the region being a picture, frame or field

Abstract

Various embodiments relate generally to a system, a device and a method for optimizing processes for compressing media content. An uncompressed content item is received in a media content management system. One or more parameters associated with the uncompressed content item are determined. A plurality of variants of the uncompressed content item is generated using the one or more parameters, the plurality of variants including one or more compressed content items. A candidate set comprising at least one of the one or more compressed content items is determined from the plurality of variants based on one or more filtering factors. A validated compressed content item is selected from the candidate set based on one or more validation criteria, and the validated compressed content item is stored in a database in the media content management system.

Claims

1. A method comprising:

receiving an uncompressed content item in an media content management system;

determining one or more parameters associated with the uncompressed content item;

generating, by a processor, a plurality of variants of the uncompressed content item using the one or more parameters, the plurality of variants including one or more compressed content items;

determining a candidate set comprising at least one of the one or more compressed content items from the plurality of variants based on one or more filtering factors;

selecting a validated compressed content item from the candidate set based on one or more validation criteria; and

storing the validated compressed content item in a database in the media content management system, wherein;

the uncompressed content item comprises a video file,

the validated compressed content item comprises a graphics interchange format (GIF) file, and

selecting the validated compressed content item from the candidate set based on the one or more validation criteria comprises determining the one or more validation criteria using a machine learning classifier that outputs an optimal set of parameter values of the one or more parameters.

2. The method of claim 1, wherein generating a plurality of variants of the uncompressed content item using the one or more parameters further comprises:

using a grid search optimization algorithm to generate the plurality of variants based on the one or more parameters and a performance metric comprising a set of parameter values based on a previously validated content item.

3. The method of claim 1, wherein the one or more parameters associated with the uncompressed content item comprises a noise parameter.

4. The method of claim 1, wherein the one or more parameters associated with the uncompressed content item comprises a smoothness parameter.

5. The method of claim 1, wherein the one or more parameters associated with the uncompressed content item comprises a sharpness parameter.

6. The method of claim 1, wherein the one or more parameters associated with the uncompressed content item comprises a color fidelity parameter.

7. The method of claim 1, wherein the one or more filtering factors used to determine the candidate set comprises a file size threshold.

8. The method of claim 1, wherein the one or more filtering factors used to determine the candidate set comprises one or more visual quality standards, wherein the one or more visual quality standards comprise a range of quality scores based on at least one performance metric.

9. The method of claim 1, wherein generating the plurality of variants of the uncompressed content item further comprises:

generating a grid comprising the plurality of variants, each variant based on a unique combination of the one or more parameters.

10. The method of claim 9, wherein the candidate set comprising at least one of the one or more compressed content items is determined using a grid search optimization algorithm.

11. A method comprising:

receiving, in an media content management system, an uncompressed content item comprising a plurality of frames;

determining data representing a color map associated with the plurality of frames of the uncompressed content item;

generating, by a processor for each frame of the plurality of frames, a plurality of color values associated with a plurality of pixels of the each frame;

comparing, by the processor for each pixel in each frame of the plurality of frames, a subset of the plurality of color values to determine a color difference value;

determining data representing a new color map associated with the plurality of frames based on the color difference value associated with each pixel in each frame; and

storing the data representing the new color map in association with the uncompressed content item to form a compressed content item in a database in the media content management system.

12. The method of claim 11, wherein the data representing a color map associated with the plurality of frames is a metadata attribute of the uncompressed content item.

13. The method of claim 11, wherein the data representing a color map associated with the plurality of frames is determined based on an analysis of each frame.

14. The method of claim 11, wherein a color difference value is determined as a percentage change in color value among the subset of the plurality of color values associated with each pixel in each frame.

15. A system comprising:

a server configured to receive an uncompressed content item comprising a plurality of frames;

a preprocessing module configured to determine data representing a color map associated with the plurality of frames of the uncompressed content item, generate a plurality of color values associated with a plurality of pixels in the plurality of frames, and the preprocessing module further configured to determine data representing a new color map based on a plurality of color difference values using the plurality of color values;

a processor configured to determine one or more parameters associated with the uncompressed content item, to generate a plurality of variants of the uncompressed content item using the one or more parameters, the plurality of variants including one or more compressed content items, to determine a candidate set comprising at least one of the one or more compressed content items based on one or more filtering factors, and the processor further configured to select a validated compressed content item from the candidate set based on one or more validation criteria;

; and

a database configured to store, by the processor, the validated compressed content item and the data representing the new color map in association with the uncompressed content item.

16. The system of claim 15, wherein the server is further configured to receive a search query, retrieve at least two compressed content items in the database, generate at least two renderings of the at least two compressed content items in animation in response to the received search query, and provide to display concurrently the at least two renderings of the at least two compressed content items in animation.

17. The system of claim 15, wherein the processor is further configured to determine the candidate set comprising at least one of the one or more compressed content items using a grid search optimization algorithm.

18. The system of claim 15, wherein the processor is further configured to generate the plurality of variants of the uncompressed content item by generating a grid comprising the plurality of variants, each variant based on a unique combination of the one or more parameters.

19. The system of claim 15, wherein the preprocessing module is further configured to determine a color difference value as a percentage change in color value among the subset of the plurality of color values associated with each pixel in each frame.