Information processing device, information processing method, and program

An information processing method performed by an information processing device which performs personal authentication based on a video signal obtained through imaging of an object person, the method comprising:

• a first feature amount calculation step of calculating a feature amount of a face of a registrant in an image of the video signal obtained through imaging of the registrant in a registration mode;
• a second feature amount calculation step of calculating time series of feature amount of a lip of the registrant in an image of the video signal obtained through imaging of the registrant speaking an arbitrary password in the registration mode;
• a registration step of registering the calculated time series of feature amount of the lip when the arbitrary password is spoken in a database to be associated with the calculated feature amount of the face of the registrant;
• an identification step of calculating a feature amount of a face in an image of the video signal obtained through imaging of the object person, referencing the database, and identifying the face of the object person in an authentication mode;
• a recognition step of calculating time series of feature amount of a lip of the object person in an image of the video signal obtained through imaging of the object person while speaking, referencing the database, and recognizing speech content of the object person in the authentication mode;
• and
• an authentication step of performing personal authentication of the object person based on an identification result of the face of the object person and a recognition result of the speech content of the object person.

A program for controlling an information processing device which performs personal authentication based on a video signal obtained through imaging of an object person, the program making a computer of the information processing device execute a process comprising:

• a first feature amount calculation step of calculating a feature amount of a face of a registrant in an image of the video signal obtained through imaging of the registrant in a registration mode;
• a second feature amount calculation step of calculating time series of feature amount of a lip of the registrant in an image of the video signal obtained through imaging of the registrant speaking an arbitrary password in the registration mode;
• a registration step of registering the calculated time series of feature amount of the lip when the arbitrary password is spoken in a database to be associated with the calculated feature amount of the face of the registrant;
• an identification step of calculating a feature amount of a face in an image of the video signal obtained through imaging of the object person, referencing the database, and identifying the face of the object person in an authentication mode;
• a recognition step of calculating time series of feature amount of a lip of the object person in an image of the video signal obtained through imaging of the object person while speaking, referencing the database, and recognizing speech content of the object person in the authentication mode;
• and
• an authentication step of performing personal authentication of the object person based on an identification result of the face of the object person and a recognition result of the speech content of the object person.

An information processing device which performs personal authentication based on a video signal obtained through imaging of an object person, comprising:

• an imaging unit configured to perform imaging of one of the object person and a registrant to generate the video signal;
• a first feature amount calculation unit configured to calculate a feature amount of a face of the registrant in an image of the video signal obtained through imaging of the registrant in a registration mode;
• a second feature amount calculation unit configured to calculate time series of feature amount of a lip of the registrant in an image of the video signal obtained through imaging of the registrant speaking an arbitrary password in the registration mode;
• a registration unit configured to register the calculated time series of feature amount of the lip when the arbitrary password is spoken in a database to be associated with the calculated feature amount of the face of the registrant;
• an identification unit configured to calculate a feature amount of a face in an image of the video signal obtained through imaging of the object person, reference the database, and identify the face of the object person in an authentication mode;
• a recognition unit configured to calculate time series of feature amount of a lip of the object person in an image of the video signal obtained through imaging of the object person while speaking, reference the database, and recognize speech content of the object person in the authentication mode;
• and
• an authentication unit configured to perform personal authentication of the object person based on an identification result of the face of the object person and a recognition result of the speech content of the object person.