Granted Patent B2

US 12,307,810 · App. 17/437,213 · Granted May 20, 2025

Inventors: Yuichi Suzuki (Kanagawa, JP); Satoshi Toriiwa (Kanagawa, JP); Kento Yamamoto (Kanagawa, JP)

Assignee: SONY SEMICONDUCTOR SOLUTIONS CORPORATION

G06V40/161G06T7/30G06T7/60G06T7/70G06T2207/20084G06T2207/30201

Abstract

Claims (95)

1. An information processing apparatus, comprising:

an image capturing apparatus configured to capture an image associated with a subject; and

a processing unit configured to:

determine image information based on a plurality of registration images, wherein the plurality of registration images is associated with the subject;

instruct the subject to perform an operation;

detect the operation of the subject, wherein the detected operation of the subject corresponds to a movement of a human face of the subject;

specify a distortion of the subject based on position information and direction information, wherein

the position information indicates a position of the subject included in the captured image,

the direction information indicates a direction of the subject, and

the subject is included in a peripheral portion of the captured image;

identify a shape of the subject based on the specified distortion of the subject and the detected operation of the subject;

collate the determined image information with the position information and the direction information;

generate a first collation image based on the collation;

determine an authentication score based on the generated first collation image; and

authenticate the subject based on the authentication score.

2. The information processing apparatus according to claim 1 , wherein the processing unit is further configured to:

generate a subject image that corresponds to an area of the subject;

generate, based on the position information and the direction information, a second collation image from a specific registration image of the plurality of registration images;

collate the generated subject image with the second collation image; and

identify, based on a result of the collation, that the shape of the subject is one of a three-dimensional shape or a two-dimensional shape.

3. The information processing apparatus according to claim 2 , wherein the processing unit is further configured to:

sequentially generate, based on three-dimensional information of the specific registration image, the second collation image and the specific registration image; and

sequentially change the direction of the subject.

4. The information processing apparatus according to claim 3 , wherein the processing unit is further configured to:

sequentially collate the generated second collation image with the subject image; and

identify the shape of the subject based on the result of the collation and the second collation image.

5. The information processing apparatus according to claim 1 , wherein the processing unit is further configured to determine that the subject is three-dimensional, based on the detected operation of the subject is the movement of the human face of the subject.

6. The information processing apparatus according to claim 1 , wherein the processing unit is further configured to:

generate a subject image that corresponds to an area of the subject included in the captured image;

correct the generated subject image based on the direction information;

collate the corrected subject image with a specific registration image of the plurality of registration images; and

identify, based on a result of the collation, that the shape of the subject is one of a three-dimensional shape or a two-dimensional shape.

7. The information processing apparatus according to claim 6 , wherein the direction information is obtained through a neural network that

inputs, to an input layer of the neural network, the subject image and the position information, and

outputs the direction information from an output layer of the neural network.

8. The information processing apparatus according to claim 7 , wherein in learning of the neural network, the direction information is included in a learning parameter.

9. The information processing apparatus according to claim 1 , wherein the processing unit is further configured to:

generate a subject image that corresponds to an area of the subject; and

acquire a result of the identification of the shape of the subject through a neural network, wherein the neural network

inputs, to an input layer of the neural network, the position information, the generated subject image, and a specific registration image of the plurality of registration images, and

outputs, from an output layer of the neural network, the result of the determination of the shape of the subject.

10. The information processing apparatus according to claim 9 , wherein in learning of the neural network, the direction information is included in a learning parameter.

11. The information processing apparatus according to claim 1 , wherein

the information processing apparatus is associated with a first mode and a second mode,

in the first mode an identification process is valid,

the identification process is associated with the identification of the shape of the subject, and

in the second mode the identification process is invalid.

12. The information processing apparatus according to claim 1 , wherein

the processing unit is further configured to determine that the human face included in the captured image is a real face.

13. The information processing apparatus according to claim 1 , wherein

the image capturing apparatus corresponds to a camera,

the camera includes a wide-angle lens,

the distortion of the subject includes a distortion of the captured image, and the captured image corresponds to the wide-angle lens.

14. An information processing method, comprising:

capturing, by the an image capturing apparatus, an image associated with a subject;

determining, by an information processing apparatus, image information based on a plurality of registration images, wherein the plurality of registration images is associated with the subject;

instructing, by the information processing apparatus, the subject to perform an operation;

detecting, by the information processing apparatus, the operation of the subject, wherein the detected operation of the subject corresponds to a movement of a human face of the subject;

specifying, by the information processing apparatus, a distortion of the subject based on position information and direction information, wherein

the position information indicates a position of the subject included in the captured image,

the direction information indicates a direction of the subject, and

the subject is included in a peripheral portion of the captured image;

identifying, by the information processing apparatus, a shape of the subject based on the specified distortion of the subject and the detected operation of the subject;

collating, by the information processing apparatus, the determined image information with the position information and the direction information;

generating, by the information processing apparatus, a first collation image based on the collation;

determining, by the information processing apparatus, an authentication score based on the generated first collation image; and

authenticating, by the information processing apparatus, the subject based on the authentication score.

15. An information processing system, comprising:

an image capturing apparatus configured to capture an image associated with a subject;

an information processing apparatus configured to:

determine image information based on a plurality of registration images, wherein the plurality of registration images is associated with the subject:

instruct the subject to perform an operation;

detect the operation of the subject, wherein the detected operation of the subject corresponds to a movement of a human face of the subject;

specify a distortion of the subject based on position information and direction information, wherein

the position information indicates a position of the subject included in the captured image,

the direction information indicates a direction of the subject, and

the subject is included in a peripheral portion of the captured image;

identify a shape of the subject based on the specified distortion of the subject and the detected operation of the subject;

collate the determined image information with the position information and the direction information;

generate a first collation image based on the collation;

determine an authentication score based on the generated first collation image; and

authenticate the subject based on the authentication score.

16. The information processing system according to claim 15 , further comprising;

a database configured to store the plurality of registration images, wherein the information processing apparatus is further configured to:

generate a subject image that corresponds to an area of the subject, wherein the subject is included in the captured image;

generate, based on the position information and the direction information, a second collation image from a specific registration image of the plurality of registration images;

collate the generated subject image with the second collation image; and

identify, based on a result of the collation, that the shape of the subject is one of a three-dimensional shape or a two-dimensional shape.

17. The information processing system according to claim 15 , further comprising;

a database configured to store the plurality of registration images, wherein the information processing apparatus is further configured to:

generate a subject image that corresponds to an area of the subject;

correct the generated subject image based on the direction information;

collate the corrected subject image and a specific registration image of the plurality of registration images; and

identify, based on a result of the collation, that the shape of the subject is one of a three-dimensional shape or a two-dimensional shape.

18. The information processing apparatus according to claim 5 , wherein the movement of the human face of the subject includes at least one of a blinking operation of an eye of the subject, an opening operation of a mouth of the subject, or a closing operation of the mouth of the subject.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (18)

Cited By (1)

US 12,561,770