Detecting segments of a video program through image comparisons

Patent metadata

Field	Value
Publication number	US-9727788-B2
Application number	US-201615228143-A
Country	US
Kind code	B2
Filing date	Aug 4, 2016
Priority date	Mar 17, 2015
Publication date	Aug 8, 2017
Grant date	Aug 8, 2017

Abstract

In an embodiment, a data store storing a first image and a second image; a computer processor coupled to the data store and programmed to: generate a first fingerprint of the first image based on a first plurality of pixels from the first image stored in the data store; generate a second fingerprint of the second image based on a second plurality of pixels from the second image stored in the data store; determine a closeness value between the first fingerprint and the second fingerprint; determine, based on the closeness value, whether the first image matches the second image.

First claim

What is claimed is:

1. An image processing system comprising:
a digital data store storing a first image and a second image;
a computer processor coupled to the data store and programmed to:
generate a first fingerprint of the first image based on a first plurality of pixels from the first image stored in the data store;
generate a second fingerprint of the second image based on a second plurality of pixels from the second image stored in the data store;
determine a closeness value between the first fingerprint and the second fingerprint;
determine, based on the closeness value, whether the first image matches the second image.

2. The image processing system of claim 1 , wherein the first fingerprint of the first image is a first color distribution based on the first plurality of pixels;
wherein the second fingerprint of the second image is a second color distribution based on the second plurality of pixels.

3. The image processing system of claim 2 , wherein the first plurality of pixels is defined within a color space comprising a first color component and a second color component;
wherein the first color distribution comprises a first color-component distribution based on the first color component of the first plurality of pixels; and a second color-component distribution based on the second color component of the first plurality of pixels.

4. The image processing system of claim 2 , wherein the second plurality of pixels is defined within a color space comprising a first color component and a second color component;
wherein the second color distribution comprises a first color-component distribution based on the first color component of the second plurality of pixels; and a second color-component distribution based on the second color component of the second plurality of pixels.

5. The image processing system of claim 1 , wherein the first fingerprint of the first image comprises a plurality of color-component distributions based on the first plurality of pixels;
wherein the second fingerprint of the second image comprises a plurality of color-component distributions based on the second plurality of pixels.

6. The image processing system of claim 1 , wherein the closeness value comprises a closeness vector or an aggregate closeness value.

7. The image processing method of claim 1 , wherein the first fingerprint of the first image comprises a first histogram based on the first plurality of pixels;
wherein the second fingerprint of the second image comprises a second histogram based on the second plurality of pixels.

8. The image processing system of claim 1 , wherein the computer processor is programmed to:
identify a first number of one or more first features in the first image;
identify a second number of one or more second features in the second image;
wherein the first fingerprint of the first image comprises the first number;
wherein the second fingerprint of the second image comprises the second number;
wherein determining the closeness value between the first fingerprint and the second fingerprint is based on the first number of one or more first features in the first image and the second number of one or more second features in the second image.

9. The image processing system of claim 8 , wherein the one or more first features in the first image are one or more first faces, and the one or more second features in the second image are one or more second faces.

10. The image processing system of claim 8 , wherein the one or more first features in the first image are one or more first characters, and the one or more second features in the second image are one or more second characters.

11. An image processing method, comprising:
using a computer processor coupled to a digital data store storing a first image and a second image, generating a first fingerprint of a first image based on a first plurality of pixels from the first image;
generating a second fingerprint of a second image using the computer processor based on a second plurality of pixels from the second image stored in the data store;
determining a closeness value between the first fingerprint and the second fingerprint using the computer processor;
determining, based on the closeness value and using the computer processor, whether the first image matches the second image.

12. The image processing method of claim 11 , wherein generating the first fingerprint of the first image comprises generating a first color distribution based on the first plurality of pixels;
wherein generating the second fingerprint of the second image comprises generating a second color distribution based on the second plurality of pixels.

13. The image processing method of claim 12 , further comprising:
identifying a first color component of the first color distribution based on the first plurality of pixels;
identifying a second color component of the first color distribution based on the first plurality of pixels;
identifying a first color component of the second color distribution based on the second plurality of pixels;
identifying a second color component of the second color distribution based on the second plurality of pixels.

14. The image processing method of claim 13 , further comprising:
identifying a third color component of the first color distribution based on the first plurality of pixels;
identifying a third color component of the second color distribution based on the second plurality of pixels.

15. The image processing method of claim 11 , wherein generating the first fingerprint of the first image comprises identifying a plurality of color-component distributions based on the first plurality of pixels;
wherein generating the second fingerprint of the second image comprises identifying a plurality of color-component distributions based on the second plurality of pixels.

16. The image processing method of claim 11 , wherein determining, based on the closeness value, whether the first image matches the second image comprises comparing the closeness value to a threshold value.

17. The image processing method of claim 11 , wherein generating the first fingerprint of the first image comprises generating a first histogram based on the first plurality of pixels;
wherein generating the second fingerprint of the second image comprises generating a second histogram based on the second plurality of pixels.

18. The image processing method of claim 11 , wherein generating the first fingerprint of the first image comprises identifying a first number of one or more first features in the first image wherein the first fingerprint of the first image comprises the first number;
wherein generating the second fingerprint of the second image comprises identifying a second number of one or more second features in the second image wherein the second fingerprint of the second image comprises the second number;
wherein determining the closeness value between the first fingerprint and the second fingerprint is based on the first number of one or more first features in the first image and the second number of one or more second features in the second image.

19. The image processing method of claim 11 , wherein generating the first fingerprint of the first image comprises identifying one or more first features in the first image that define one or more first faces;
wherein generating the second fingerprint of the second image comprises identifying one or more second features in the second image that define one or more second faces.

20. The

Assignees

• Netflix Inc
• Netflix Inc

Inventors

• Kansara Apurvakumar

Classifications

• H04N21/23418 Primary

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title

• G06V10/75

  Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries · CPC title

• G06V20/46 Primary

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title