RELIABILITY ACQUIRING APPARATUS, RELIABILITY ACQUIRING METHOD, AND RELIABILITY ACQUIRING PROGRAM

• US 20150023606A1
• Filed: 02/08/2013
• Published: 01/22/2015
• Est. Priority Date: 02/16/2012
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NRC Limited
• Inventors: Morishita, Yusuke
• Granted Patent: US 9,858,501 B2
• Time in Patent Office: Days
• US Class Current: 382/219
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

A reliability acquiring apparatus includes a section that stores information on a classifier that outputs part likelihood concerning a predetermined part of a detection target when applied to an image, a section that calculates, concerning an image region included in an input image, the part likelihood on the basis of the information on the classifier, a section that determines, on the basis of the calculated part likelihood, a position of the predetermined part in the input image, a section that stores information on a reference position of the predetermined part, a section that calculates, on the basis of the information on the reference position, difference information between the reference position of the predetermined part and the determined position of the predetermined part, and a section that calculates, on the basis of the difference information, reliability indicating possibility that the input image is an image of the detection target.

Claims

1. A reliability acquiring apparatus comprising:

a classifier storing section that stores information on a classifier that outputs part likelihood concerning a predetermined part of a detection target when applied to an image;

a part likelihood acquiring section that calculates, concerning an image region included in an input image, the part likelihood on the basis of the information on the classifier;

a part position determining section that determines, on the basis of the calculated part likelihood, a position of the predetermined part in the input image;

a reference position information storing section that stores information on a reference position of the predetermined part;

a difference acquiring section that calculates, on the basis of the information on the reference position, difference information between the reference position of the predetermined part and the determined position of the predetermined part; and

a reliability acquiring section that calculates, on the basis of the difference information, reliability indicating possibility that the input image is an image of the detection target.

2. The reliability acquiring apparatus according to claim 1, wherein the detection target is a face.

3. The reliability acquiring apparatus according to claim 1, wherein

the classifier storing section and the reference position information storing section respectively store, concerning a plurality of predetermined parts, information on the classifier and information on reference positions, and

the part likelihood acquiring section, the part position determining section, and the difference acquiring section respectively, concerning the predetermined parts, acquire the part likelihood, determine positions of the predetermined parts, and calculate the difference information.

4. The reliability acquiring apparatus according to claim 1, wherein the reliability acquiring section calculates the reliability on the basis of the difference information and the calculated part likelihood.

5. The reliability acquiring apparatus according to claim 1, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

6. The reliability acquiring apparatus according to claim 1, wherein the difference acquiring section calculates the difference information on the basis of whether the part position determined by the position determining section is an outlier using a method of robust estimation.

9. The reliability acquiring apparatus according to claim 2, wherein

the classifier storing section and the reference position information storing section respectively store, concerning a plurality of predetermined parts, information on the classifier and information on reference positions, and

the part likelihood acquiring section, the part position determining section, and the difference acquiring section respectively, concerning the predetermined parts, acquire the part likelihood, determine positions of the predetermined parts, and calculate the difference information.

10. The reliability acquiring apparatus according to claim 2, wherein the reliability acquiring section calculates the reliability on the basis of the difference information and the calculated part likelihood.

11. The reliability acquiring apparatus according to claim 3, wherein the reliability acquiring section calculates the reliability on the basis of the difference information and the calculated part likelihood.

12. The reliability acquiring apparatus according to claim 2, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

13. The reliability acquiring apparatus according to claim 3, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

14. The reliability acquiring apparatus according to claim 4, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

15. The reliability acquiring apparatus according to claim 2, wherein the difference acquiring section calculates the difference information on the basis of whether the part position determined by the position determining section is an outlier using a method of robust estimation.

16. The reliability acquiring apparatus according to claim 3, wherein the difference acquiring section calculates the difference information on the basis of whether the part position determined by the position determining section is an outlier using a method of robust estimation.

17. The reliability acquiring apparatus according to claim 4, wherein the difference acquiring section calculates the difference information on the basis of whether the part position determined by the position determining section is an outlier using a method of robust estimation.

18. The reliability acquiring apparatus according to claim 5, wherein the difference acquiring section calculates the difference information on the basis of whether the part position determined by the position determining section is an outlier using a method of robust estimation.

19. The reliability acquiring apparatus according to claim 10, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

20. The reliability acquiring apparatus according to claim 11, wherein the reliability acquiring section calculates integrated reliability on the basis of the reliability and one or more levels of additional reliability calculated by a method different from a method for calculating the reliability.

7. A reliability acquiring method, wherein

a computer calculates, concerning an image region included in the an input image and by referring to a classifier storing section that stores information on a classifier that outputs part likelihood concerning a predetermined part of a detection target when applied to an image, the part likelihood on the basis of the information on the classifier, determines a position of the predetermined part in the input image on the basis of the calculated part likelihood, calculates, by referring to a reference position information storing section that stores information on a reference position of the predetermined part and on the basis of the information on the reference position, difference information between the reference position of the predetermined part and the determined position of the predetermined part, and calculates possibility that the input image is an image of the detection target on the basis of the difference information.

8. A program stored on a non-transitory recording medium for causing a computer to perform steps of:

calculating, concerning an image region included in the an input image and by referring to a classifier storing section that stores information on a classifier that outputs part likelihood concerning a predetermined part of a detection target when applied to an image, the part likelihood on the basis of the information on the classifier;

determining a position of the predetermined part in the input image on the basis of the calculated part likelihood;

calculating, by referring to a reference position information storing section that stores information on a reference position of the predetermined part and on the basis of the information on the reference position, difference information between the reference position of the predetermined part and the determined position of the predetermined part; and

calculating a possibility that the input image is an image of the detection target on the basis of the difference information.