Image identification apparatus and image identification method

• US 10,699,102 B2
• Filed: 11/28/2016
• Issued: 06/30/2020
• Est. Priority Date: 12/01/2015
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Nakano, Shunsuke, Sato, Hiroshi, Kaneda, Yuji, Nomoto, Atsuo, Nishino, Daisuke, Yamamoto, Takahisa
• Primary Examiner(s): Youssef, Menatoallah
• Application Number:
  US15/362,612
• Publication Number:
  US 20170154209A1
• Time in Patent Office: 1,310 Days
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06F 18/2431 Multiple classes
• CPC Class Codes: G06F 18/2451 linear, e.g. hyperplane
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/178 estimating age from face image; using age information for improving recognition

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.

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.

2. The identification apparatus according to claim 1,

wherein the acquisition unit acquires first input face image data and second input face image data as the input face image data, and

wherein the identification unit identifies classes to which the first input face image data and the second input face image data acquired by the acquisition unit belong,

the identification apparatus further comprising a determination unit configured to determine whether the person of the first input face image data is equal to or different from the person of the second input face image data based on the person of the first input face image data and the person of the second input face image data identified by the identification unit.

3. The identification apparatus according to claim 2,

wherein each of the plurality of classifiers is configured to identify whether the input face image data belongs to a first class or a second class including all data not belonging to the first class, and

wherein the identification unit identifies the classes to which the first input face image data and the second input face image data acquired by the acquisition unit belong based on the plurality of classifiers.

4. The identification apparatus according to claim 1,

wherein the plurality of classifiers are each configured to identify whether the input face image data belongs to a first class or a second class including at least one class having been set beforehand, and

wherein the identification unit identifies the classes to which the first input face image data and the second input face image data acquired by the acquisition unit belong based on the plurality of classifiers.

5. The identification apparatus according to claim 2, wherein the identification unit identifies the classes to which the acquired first input face image data and the second input face image data belong by using the plurality of classifiers that are linear classifiers.

6. The identification apparatus according to claim 2, wherein the identification unit identifies the classes to which the acquired first input face image data and the second input face image data belong by using the plurality of classifiers that include neural networks.

7. The identification apparatus according to claim 2, wherein the identification unit identifies the classes to which the acquired first input face image data and the second input face image data belong based on a first classifier included in the plurality of classifiers, and a second classifier included in the plurality of classifiers identifies an identification result obtained by the first classifier.

8. The identification apparatus according to claim 2, wherein the determination unit determines whether the person of the first input face image data is equal to or different from the person of the second input face image data based on a comparison between a vector obtained by connecting class identification results of the first input face image data respectively identified by the plurality of classifiers and a vector obtained by connecting class identification results of the second input face image data respectively identified by the plurality of classifiers.

9. The identification apparatus according to claim 1,

wherein the acquisition unit acquires image data of a captured human face as the input face image data, and

wherein the identification unit identifies the person to which the acquired input face image data belongs based on the classifier configured to identify one of a plurality of classes, to which the data belongs, that includes classes indicating two or more individual persons having been set beforehand.

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.