Method of object orientation detection

• US 9,483,827 B2
• Filed: 01/20/2015
• Issued: 11/01/2016
• Est. Priority Date: 01/20/2014
• Status: Active Grant

• Current Assignee: Arm Limited (SoftBank Group Corp.)
• Original Assignee: Apical Limited (SoftBank Group Corp.)
• Inventors: Romanenko, Ilya
• Primary Examiner(s): Mariam, Daniel
• Application Number:
  US14/601,095
• Publication Number:
  US 20150206311A1
• Time in Patent Office: 651 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/24147 Distances to closest patterns, e.g. nearest neighbour classification
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/77 using statistical methods
• CPC Class Codes: G06V 10/446 using Haar-like filters, e.g. using integral image techniques
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships

Abstract

A method of determining an orientation of an object within an image. The method determines the responses of at least two classifiers in at least one region of the image corresponding to the object. The classifiers have been trained to identify a given object in different specific orientations. The orientation of the object is determined as an average of the specific orientations, weighted by the responses of their respective classifiers.

Claims

1. A method of determining an orientation of an object within an image, the method comprising:

determining responses of at least two classifiers in at least one region of the image corresponding to the object, the classifiers having been trained to identify the given object in different specific orientations; and

determining the orientation of the object as an average of the specific orientations, weighted by the responses of their respective classifiers, excluding specific orientations of classifiers having a response smaller than zero.

2. The method according to claim 1, comprising identifying the at least one region as a region with a response larger than zero of at least one classifier.

3. The method according to claim 1, comprising identifying the at least one region using a face detection algorithm.

4. The method according to claim 1, comprising identifying a cluster of regions for the object,

the cluster comprising at least two regions with a response larger than zero for at least one classifier, the regions having at least different sizes or different positions within the image;

and in which the weighted average is calculated over all regions of the cluster.

5. The method according to claim 1, in which at least one of the classifiers is a Haar classifier.

6. The method according to claim 1, in which at least one of the classifiers is a k-nearest neighbor'"'"'s algorithm.

7. The method according to claim 1, in which at least one of the classifiers is a support vector machine.

8. Apparatus for processing an image, the apparatus comprising:

at least one processor; and

at least one memory including computer program instructions,

the at least one memory and the computer program instructions being configured to, with the at least one processor, cause the apparatus to perform a method of determining an orientation of an object within an image, the method comprising;

determining responses of at least two classifiers in at least one region of the image corresponding to the object, the classifiers having been trained to identify the given object in different specific orientations; and

determining the orientation of the object as an average of the specific orientations, weighted by the responses of their respective classifiers, excluding specific orientations of classifiers having a response smaller than zero.

9. A non-transitory computer-readable storage medium comprising computer-executable instructions which, when executed by a processor, cause a computing device to perform a method of determining an orientation of an object within an image, the method comprising:

determining responses of at least two classifiers in at least one region of the image corresponding to the object, the classifiers having been trained to identify the given object in different specific orientations; and

determining the orientation of the object as an average of the specific orientations, weighted by the responses of their respective classifiers, excluding specific orientations of classifiers having a response smaller than zero.