Systems and methods for identifying objects in media contents

Patent metadata

Field	Value
Publication number	US-10163020-B2
Application number	US-201815997572-A
Country	US
Kind code	B2
Filing date	Jun 4, 2018
Priority date	Oct 4, 2016
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

There is provided a system configured to receive a plurality of images, analyze a set of features of the plurality of images to determine a difference between a first training performance of a plurality of independent detectors based on one or more of individual attributes and a second training performance of a plurality of joint detectors based on one or more of composite attributes, select, based on the analyzing, either one of the plurality of independent detectors or one of the plurality of joint detectors for identifying a plurality of objects in the plurality of images, and identify the plurality of objects in the plurality of images, using the selected one of the plurality of independent detectors utilizing the one or more of the individual attributes or using the selected one of the plurality of joint detectors utilizing the one or more of the composite attributes.

First claim

What is claimed is:

1. A system comprising:
a non-transitory memory storing an attribute database including individual attributes and composite attributes, each of the composite attributes including two or more of the individual attributes; and
a hardware processor executing an executable code to:
receive a plurality of images;
analyze a set of features of the plurality of images to determine a difference between a first training performance of a plurality of independent detectors and a second training performance of a plurality of joint detectors, wherein the plurality of independent detectors are for identifying a plurality of objects in the plurality of images based on one or more of the individual attributes, and wherein the plurality of joint detectors are for identifying the plurality of objects in the plurality of images based on one or more of the composite attributes;
select, based on the analyzing, either one of the plurality of independent detectors or one of the plurality of joint detectors for identifying the plurality of objects in the plurality of images; and
identify the plurality of objects in the plurality of images, using the selected one of the plurality of independent detectors utilizing the one or more of the individual attributes or using the selected one of the plurality of joint detectors utilizing the one or more of the composite attributes.

2. The system of claim 1 , wherein one attribute in the attribute database is one of a first noun, a first adjective, a first preposition, and a first verb.

3. The system of claim 2 , wherein another attribute in the attribute database is one of a second noun, a second adjective, a second preposition, and a second verb.

4. The system of claim 1 , wherein one attribute in the attribute database is a scene attribute.

5. The system of claim 1 , wherein the selecting determines a more effective detector for a given set of attributes based on results of a regression analysis.

6. A method for use with a system including a hardware processor and a non-transitory memory storing an attribute database including individual attributes and composite attributes, each of the composite attributes including two or more of the individual attributes, the method comprising:
receiving, using the hardware processor, a plurality of images;
analyzing, using the hardware processor, a set of features of the plurality of images to determine a difference between a first training performance of a plurality of independent detectors and a second training performance of a plurality of joint detectors, wherein the plurality of independent detectors are for identifying a plurality of objects in the plurality of images based on one or more of the individual attributes, and wherein the plurality of joint detectors are for identifying the plurality of objects in the plurality of images based on one or more of the composite attributes;
selecting, using the hardware processor and based on the analyzing, either one of the plurality of independent detectors or one of the plurality of joint detectors for identifying the plurality of objects in the plurality of images; and
identifying the plurality of objects in the plurality of images, using the selected one of the plurality of independent detectors utilizing the one or more of the individual attributes or using the selected one of the plurality of joint detectors utilizing the one or more of the composite attributes.

7. The method of claim 6 , wherein one attribute in the attribute database is one of a first noun, a first adjective, a first preposition, and a first verb.

8. The method of claim 7 , wherein another attribute in the attribute database is one of a second noun, a second adjective, a second preposition, and a second verb.

9. The method of claim 6 , wherein one attribute in the attribute database is a scene attribute.

10. The method of claim 6 , wherein the selecting determines a more effective detector for a given set of attributes based on results of a regression analysis.

Assignees

• Disney Entpr Inc

Inventors

• Sigal Leonid
• Shamir Arik
• Rosenthal Guy

Classifications

• G06V10/82 Primary

  using neural networks · CPC title

• G06V10/955

  using specific electronic processors · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · 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

• G06K9/00986 Primary

  Physics · mapped topic