Image processing apparatus, image processing method, and storage medium

1 . An image processing apparatus comprising:

at least one memory storing instructions; and

at least one processor that executes the stored instructions, which cause the at least one processor to:

acquire a captured image;

identify at least one fraudulent person involved in a fraudulent act from among a plurality of persons in the captured image based on at least one of a combination of behaviors of the plurality of persons and a combination of positions of the plurality of persons,

wherein the at least one fraudulent person comprises two fraudulent persons;

identify a person committing a fraudulent act as one fraudulent person of the two fraudulent persons from among the plurality of persons based on an estimation result of behaviors of the plurality of persons and identify a person aiding and abetting a fraudulent act as another fraudulent person of the two fraudulent persons based on at least one of a combination of behavior and a combination of positions of the person committing the fraudulent act and another person;

acquire an authentication image to be used in authentication processing for a person to be authenticated;

determine whether the person to be authenticated is the person committing the fraudulent act based on the authentication image; and

identify the person aiding and abetting the fraudulent act from among the plurality of persons based on a positional relationship between a camera that captures an image of the person to be authenticated and the plurality of persons.

2 . The image processing apparatus according to claim 1 , wherein the instructions further cause the at least one processor to identify the at least one fraudulent person based on the combination of behaviors of the plurality of persons or the combination of positions of the plurality of persons.

3 . The image processing apparatus according to claim 1 ,

wherein the at least one fraudulent person comprises two or more fraudulent persons, and

wherein the instructions further cause the at least one processor to identify the two or more fraudulent persons from among the plurality of persons.

4 . The image processing apparatus according to claim 1 ,

wherein the at least one fraudulent person comprises two or more fraudulent persons, and

wherein the instructions further cause the at least one processor to identify one or more persons committing a fraudulent act and one or more persons aiding and abetting a fraudulent act respectively as the two or more fraudulent persons.

5 . The image processing apparatus according to claim 1 ,

wherein the at least one fraudulent person comprises two or more fraudulent persons, and

wherein the instructions further cause the at least one processor to:

determine two or more persons who belong to a group from among the plurality of persons based on a tracking processing result of the plurality of persons, and

identify the two or more fraudulent persons based on at least one of a combination of behaviors of the two or more persons determined to belong to the group and a combination of positions of the two or more persons determined to belong to the group.

6 . The image processing apparatus according to claim 1 , wherein the instructions further cause the at least one processor to identify as the person aiding and abetting a fraudulent act a person who performs at least one of watching an area around the person committing a fraudulent act, hiding the person committing the fraudulent act from a camera, hiding the person committing the fraudulent act from a passerby, talking to a person who approaches the person committing the fraudulent act, drawing an attention of a security guard, or blocking a path of a passerby.

7 . The image processing apparatus according to claim 1 , wherein the instructions further cause the at least one processor to, in a case where a person who performs a specific behavior before or during the authentication processing is identified, change a criterion in the authentication processing so that a result of the authentication processing for the person to be authenticated is more likely to indicate failure.

8 . The image processing apparatus according to claim 1 , wherein the instructions further cause the at least one processor to perform control to display the captured image and an identification result of the at least one fraudulent person by an identification unit on a display screen.

9 . The image processing apparatus according to claim 1 , wherein the instructions further cause the at least one processor to generate a blacklist database based on an identification result of a fraudulent person.

10 . A method for image processing executed by an image processing apparatus, the method comprising:

acquiring a captured image; and

identifying at least one fraudulent person involved in a fraudulent act from among a plurality of persons in the captured image based on at least one of a combination of behaviors of the plurality of persons and a combination of positions of the plurality of persons,

wherein the at least one fraudulent person comprises two fraudulent persons;

identifying a person committing a fraudulent act as one fraudulent person of the two fraudulent persons from among the plurality of persons based on an estimation result of behaviors of the plurality of persons and identifying a person aiding and abetting a fraudulent act as another fraudulent person of the two fraudulent persons based on at least one of a combination of behavior and a combination of positions of the person committing the fraudulent act and another person;

acquiring an authentication image to be used in authentication processing for a person to be authenticated;

determining whether the person to be authenticated is the person committing the fraudulent act based on the authentication image; and

identifying the person aiding and abetting the fraudulent act from among the plurality of persons based on a positional relationship between a camera that captures an image of the person to be authenticated and the plurality of persons.

11 . The method according to claim 10 , wherein, a fraudulent person is identified based on the combination of behavior of the plurality of persons or the combination of positions of the plurality of persons.

12 . The method according to claim 10 , further comprising determining two or more persons who belong to a group from among the plurality of persons based on a tracking processing result of the plurality of persons,

wherein the at least one fraudulent person comprises two or more fraudulent persons, and

wherein, the two or more fraudulent persons are identified based on at least one of a combination of behaviors of the two or more persons determined to belong to the group and a combination of positions of the two or more persons determined to belong to the same group.

13 . The method according to claim 10 , wherein, a person who performs at least one of watching an area around the person committing the fraudulent act, hiding the person committing the fraudulent act from a camera, hiding the person committing the fraudulent act from a passerby, talking to a person who approaches the person committing the fraudulent act, drawing an attention of a security guard, or blocking a path of a passerby is identified as the person aiding and abetting the fraudulent act.

14 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute a method performed by an image processing apparatus, the method comprising:

acquiring a captured image; and

identifying at least one fraudulent person involved in a fraudulent act from among a plurality of persons in the captured image based on at least one of a combination of behaviors of the plurality of persons and a combination of positions of the plurality of persons,

wherein the at least one fraudulent person comprises two fraudulent persons;

identifying a person committing a fraudulent act as one fraudulent person of the two fraudulent persons from among the plurality of persons based on an estimation result of behaviors of the plurality of persons and identifying a person aiding and abetting a fraudulent act as another fraudulent person of the two fraudulent persons based on at least one of a combination of behavior and a combination of positions of the person committing the fraudulent act and another person;

acquiring an authentication image to be used in authentication processing for a person to be authenticated;

determining whether the person to be authenticated is the person committing the fraudulent act based on the authentication image; and

identifying the person aiding and abetting the fraudulent act from among the plurality of persons based on a positional relationship between a camera that captures an image of the person to be authenticated and the plurality of persons.