AGE ESTIMATION APPARATUS, AGE ESTIMATION METHOD, AND AGE ESTIMATION PROGRAM

• US 20120051629A1
• Filed: 04/14/2010
• Published: 03/01/2012
• Est. Priority Date: 04/28/2009
• Status: Active Grant

• Current Assignee: Tokyo Institute of Technology (National University Corporation Tokyo Institute of Technology), NEC Solution Innovators, Ltd (NEC Corporation)
• Original Assignee: NEC Solution Innovators, Ltd (NEC Corporation)
• Inventors: Ueki, Kazuya, Sugiyama, Masashi, Ihara, Yasuyuki
• Granted Patent: US 8,818,111 B2
• Time in Patent Office: Days
• US Class Current: 382/159
• CPC Class Codes: G06F 18/2414 Smoothing the distance, e.g. radial basis function networks [RBFN]
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/178 estimating age from face image; using age information for improving recognition

Abstract

Provided are an age estimation apparatus, an age estimation method, and an age estimation program capable of reducing the labor of labeling the image data used for age estimation. An age estimation apparatus for estimating an age of a person on image data includes a dimension compression unit for applying dimension compression to the image data to output low dimensional data; a clustering unit for performing clustering of the low dimensional data outputted; a labeling unit for labeling representative data of each cluster among the low dimensional data clustered; and an identification unit for estimating an age of a person on the basis of a learning result using a feature amount contained in labeled low dimensional data and unlabeled low dimensional data.

Claims

1. An age estimation apparatus for estimating an age of a person on image data, comprising:

a dimension compression unit for applying dimension compression to the image data to output low dimensional data;

a clustering unit for performing clustering of the low dimensional data outputted;

a labeling unit for labeling representative data of each cluster among the low dimensional data clustered; and

an identification unit for estimating an age of a person on the basis of a learning result using a feature amount contained in labeled low dimensional data and unlabeled low dimensional data.

2. The apparatus according to claim 1, wherein

a parameter used for the dimension compression by the dimension compression unit and the feature amount used for age estimation by the identification unit are set on the basis of a result of an evaluation of a generalization capability using a weighting function that shows a degree of seriousness of an estimated age error for every age, and

learning of the identification unit is performed on the basis of the weighting function.

3. The apparatus according to claim 2, wherein the evaluation of the generalization capability is made on the basis of a weighted mean square error.

4. The apparatus according to claim 2, wherein the weighting function is defined on the basis of a standard deviation of each perceptual age.

5. The apparatus according to claim 2, wherein the smaller the value of the weight function is, the more serious the estimated age error.

6. An age estimation method for estimating an age of a person on image data, comprising:

a dimension compression step for applying dimension compression to the image data to output low dimensional data;

a clustering step for performing clustering of the low dimensional data outputted;

a labeling step for labeling representative data of each cluster among the low dimensional data clustered; and

an identification step for estimating an age of a person on the basis of a learning result using a feature amount contained in labeled low dimensional data and unlabeled low dimensional data.

7. The method according to claim 6, wherein

a parameter used for the dimension compression in the dimension compression step and the feature amount used for age estimation in the identification step are set on the basis of a result of an evaluation a generalization capability using a weighting function that shows a degree of seriousness of an estimated age error for every age, and

an identification device conducting the identification step is made to learn on the basis of the weighting function.

8. The method according to claim 7, wherein the evaluation of the generalization capability is made on the basis of a weighted mean square error.

9. The method according to claim 7, wherein the weighting function is defined on the basis of a standard deviation of each perceptual age.

10. The method according to claim 7, wherein the smaller the value of the weighting function is, the more serious the estimated age error.

11. An age estimation program for estimating an age of a person on image data, wherein

a computer is caused to execute

dimension compression processing of applying dimension compression to the image data to output low dimensional data;

clustering processing of performing clustering of the low dimensional data outputted;

labeling processing of labeling representative data of each cluster among the low dimensional data clustered; and

identification processing of estimating an age of a person on the basis of a learning result using a feature amount contained in labeled low dimensional data and unlabeled low dimensional data.

12. The program according to claim 11, wherein

a parameter used for the dimension compression in the dimension compression processing and the feature amount used for age estimation in the identification processing are set on the basis of a result of an evaluation a generalization capability using a weighting function that shows a degree of seriousness of an estimated age error for every age, and

the computer is caused to execute processing of learning of the identification device conducting the identification processing on the basis of the weighting function.

13. The program according to claim 12, wherein the computer is caused to execute processing of making the evaluation of the generalization capability on the basis of a weighted mean square error.

14. The program according to claim 12, wherein the computer is caused to execute processing of defining the weighting function on the basis of a standard deviation of each perceptual age.

15. The program according to claim 12, wherein the smaller the value of the weighting function is, the more serious the estimated age error.