Apparatus, method, and program for discriminating subjects
First Claim
1. A subject discriminating apparatus comprising:
- an image input means for receiving input of a target image, which is a target of discrimination;
a first characteristic amount calculating means for calculating first characteristic amounts, which do not require normalization and are employed to discriminate a predetermined subject, from the target image;
a first discriminating means for discriminating whether a candidate of the predetermined subject is included in the target image, by referring to first reference data, in which the first characteristic amounts and discrimination conditions corresponding to the first characteristic amounts are defined in advance, with the first characteristic amounts calculated from the target image;
a second characteristic amount calculating means for calculating second characteristic amounts, which are normalized and employed to discriminate the predetermined subject, from the candidate of the predetermined subject in the case that the first discriminating means judges that the candidate is included in the target image; and
a second discriminating means for discriminating whether the candidate is the predetermined subject, by referring to second reference data, in which the second characteristic amounts and discrimination conditions corresponding to the second characteristic amounts are defined in advance, with the normalized second characteristic amounts.
2 Assignments
0 Petitions
Accused Products
Abstract
A characteristic amount calculating means calculates first characteristic amounts, which do not require normalization, and normalized second characteristic amounts. A first discriminating portion discriminates whether a candidate for a face is included in the target image, by referring to first reference data with the first characteristic amounts, calculated from the target image. The first reference data is obtained by learning the first characteristic amounts of a plurality of images, which are known either to be of faces or to not be of faces. In the case that the candidate is included, a second discriminating portion discriminates whether the candidate is a face, by referring to second reference data, obtained by learning the second characteristic amounts of a plurality of images, which known either to be of faces or to not to be of faces.
131 Citations
39 Claims
-
1. A subject discriminating apparatus comprising:
-
an image input means for receiving input of a target image, which is a target of discrimination;
a first characteristic amount calculating means for calculating first characteristic amounts, which do not require normalization and are employed to discriminate a predetermined subject, from the target image;
a first discriminating means for discriminating whether a candidate of the predetermined subject is included in the target image, by referring to first reference data, in which the first characteristic amounts and discrimination conditions corresponding to the first characteristic amounts are defined in advance, with the first characteristic amounts calculated from the target image;
a second characteristic amount calculating means for calculating second characteristic amounts, which are normalized and employed to discriminate the predetermined subject, from the candidate of the predetermined subject in the case that the first discriminating means judges that the candidate is included in the target image; and
a second discriminating means for discriminating whether the candidate is the predetermined subject, by referring to second reference data, in which the second characteristic amounts and discrimination conditions corresponding to the second characteristic amounts are defined in advance, with the normalized second characteristic amounts. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A subject discriminating method comprising the steps of:
-
receiving input of a target image, which is a target of discrimination;
calculating first characteristic amounts, which do not require normalization and are employed to discriminate a predetermined subject, from the target image;
discriminating whether a candidate of the predetermined subject is included in the target image, by referring to first reference data, in which the first characteristic amounts and discrimination conditions corresponding to the first characteristic amounts are defined in advance, with the first characteristic amounts calculated from the target image;
calculating second characteristic amounts, which are normalized and employed to discriminate the predetermined subject, from the candidate of the predetermined subject in the case that the first discriminating means judges that the candidate is included in the target image; and
discriminating whether the candidate is the predetermined subject, by referring to second reference data, in which the second characteristic amounts and discrimination conditions corresponding to the second characteristic amounts are defined in advance, with the normalized second characteristic amounts.
-
-
16. A program that causes a computer to execute a subject discriminating method, comprising the procedures of:
-
receiving input of a target image, which is a target of discrimination;
calculating first characteristic amounts, which do not require normalization and are employed to discriminate a predetermined subject, from the target image;
discriminating whether a candidate of the predetermined subject is included in the target image, by referring to first reference data, in which the first characteristic amounts and discrimination conditions corresponding to the first characteristic amounts are defined in advance, with the first characteristic amounts calculated from the target image;
calculating second characteristic amounts, which are normalized and employed to discriminate the predetermined subject, from the candidate of the predetermined subject in the case that the first discriminating means judges that the candidate is included in the target image; and
discriminating whether the candidate is the predetermined subject, by referring to second reference data, in which the second characteristic amounts and discrimination conditions corresponding to the second characteristic amounts are defined in advance, with the normalized second characteristic amounts. - View Dependent Claims (37)
-
-
17. A subject discriminating apparatus comprising:
-
an image input means for receiving a target image, which is a target of discrimination;
a characteristic amount calculating means for calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
a first discriminating means for discriminating whether the predetermined subject is included in the target image, by referring to first reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the first reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique; and
a second discriminating means for discriminating the positions of the at least one structural component included in the target image, by referring to second reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a second predetermined allowable range which is smaller than the first allowable range in the case that the first discriminating means judges that the predetermined subject is included in the target image, wherein the second reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the second predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24, 25)
-
-
26. A subject discriminating method, comprising the steps of:
-
receiving a target image, which is a target of discrimination;
calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
discriminating whether the predetermined subject is included in the target image, by referring to first reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the first reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique; and
discriminating the positions of the at least one structural component included in the target image, by referring to second reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a second predetermined allowable range which is smaller than the first allowable range in the case that the first discriminating means judges that the predetermined subject is included in the target image, wherein the second reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the second predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique.
-
-
27. A program that causes a computer to execute a subject discriminating method, comprising the procedures of:
-
receiving a target image, which is a target of discrimination;
calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
discriminating whether the predetermined subject is included in the target image, by referring to first reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the first reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique; and
discriminating the positions of the at least one structural component included in the target image, by referring to second reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image while the target image is deformed in a stepwise manner within a variance corresponding to a second predetermined allowable range which is smaller than the first allowable range in the case that the first discriminating means judges that the predetermined subject is included in the target image, wherein the second reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the second predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique. - View Dependent Claims (38)
-
-
28. A subject discriminating apparatus comprising:
-
an image input means for receiving input of a target image, which is a target of discrimination;
a characteristic amount calculating means for calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
a discriminating means for discriminating whether the predetermined subject is included in the target image, by referring to reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image, while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique, and for discriminating the positions of the at least one structural component included in the predetermined subject in the case that the predetermined subject is included in the target image. - View Dependent Claims (29, 30, 31, 32, 33, 34)
-
-
35. A subject discriminating method, comprising the steps of:
-
receiving input of a target image, which is a target of discrimination;
calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
discriminating whether the predetermined subject is included in the target image, by referring to reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image, while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique; and
discriminating the positions of the at least one structural component included in the predetermined subject, in the case that the predetermined subject is included in the target image.
-
-
36. A program that causes a computer to execute a subject discriminating method, comprising the procedures of:
-
receiving input of a target image, which is a target of discrimination;
calculating at least one characteristic amount, which is employed in discriminating a predetermined subject that includes at least one structural component, from the target image;
discriminating whether the predetermined subject is included in the target image, by referring to reference data in which the at least one characteristic amount and discrimination conditions corresponding to the at least one characteristic amount are defined in advance, with the at least one characteristic amount calculated from the target image, while the target image is deformed in a stepwise manner within a variance corresponding to a first predetermined allowable range, wherein the reference data is obtained by learning the at least one characteristic amount within a plurality of sample images, in which the positions and/or the positional relationships of the at least one structural component are normalized within the first predetermined allowable range, and a plurality of sample image groups, which are known to not include the predetermined subject, with a machine learning technique; and
discriminating the positions of the at least one structural component included in the predetermined subject, in the case that the predetermined subject is included in the target image. - View Dependent Claims (39)
-
Specification