Image identification apparatus and image identification method
First Claim
Patent Images
1. An identification apparatus comprising:
- at least one memory; and
one or more processors in communication with the at least one memory, the one or more processors configured to provide;
an acquisition unit configured to acquire input face image data;
a plurality of binary classifiers each of which is configured to classify the input face image data into one of respective two groups of persons, wherein the respective two groups for the plurality of binary classifiers are independent and members of the respective two groups are selected from a set of predetermined persons without specifying their common attributes, and at least one of the two groups of persons for at least one of the plurality of binary classifiers includes two or more persons; and
an identification unit configured to identify a person to which the input face image data belongs based on a combination of groups of persons, where each group in the combination of the groups corresponds to a classification result of the input face image data obtained by respective one of the plurality of binary classifiers.
1 Assignment
0 Petitions
Accused Products
Abstract
An identification apparatus includes an acquisition unit configured to acquire input data and an identification unit configured to identify a class to which the acquired input data belongs based on a classifier configured to identify a class to which the data belongs from among a plurality of classes that includes two or more classes having been set beforehand.
4 Citations
11 Claims
-
1. An identification apparatus comprising:
-
at least one memory; and one or more processors in communication with the at least one memory, the one or more processors configured to provide; an acquisition unit configured to acquire input face image data; a plurality of binary classifiers each of which is configured to classify the input face image data into one of respective two groups of persons, wherein the respective two groups for the plurality of binary classifiers are independent and members of the respective two groups are selected from a set of predetermined persons without specifying their common attributes, and at least one of the two groups of persons for at least one of the plurality of binary classifiers includes two or more persons; and an identification unit configured to identify a person to which the input face image data belongs based on a combination of groups of persons, where each group in the combination of the groups corresponds to a classification result of the input face image data obtained by respective one of the plurality of binary classifiers. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An information processing method for an identification apparatus, the method comprising:
-
acquiring input face image data; using a plurality of binary classifiers each of which is configured to classify the input face image data into one of respective two groups of persons, wherein the respective two groups for the plurality of binary classifiers are independent and members of the respective two groups are selected from a set of predetermined persons without specifying their common attributes, and at least one of the two groups of persons for at least one of the plurality of binary classifiers includes two or more persons; and identifying a person to which the input face image data belongs based on a combination of groups of persons, where each group in the combination of the groups corresponds to a classification result of the input face image data obtained by respective one of the plurality of binary classifiers.
-
-
11. A non-transitory computer-readable storage medium storing a program that causes a computer to execute an information processing method for an identification apparatus, the method comprising:
-
acquiring input face image data; using a plurality of binary classifiers each of which is configured to classify the input face image data into one of respective two groups of persons, wherein the respective two groups for the plurality of binary classifiers are independent and members of the respective two groups are selected from a set of predetermined persons without specifying their common attributes, and at least one of the two groups of persons for at least one of the plurality of binary classifiers includes two or more persons; and identifying a person to which the input face image data belongs based on a combination of groups of persons, where each group in the combination of the groups corresponds to a classification result of the input face image data obtained by respective one of the plurality of binary classifiers.
-
Specification