Personal authentication apparatus and personal authentication method
A personal authentication apparatus includes a facial region extraction which extracts an image of a facial region of a person obtained from image sensing input unit, a guide unit which guides motion of the person of interest, a feature amount extraction unit which extracts the feature amount of a face from the image of the facial region extracted by the facial region extraction unit while the motion is guided by the guide unit, a dictionary registration unit which registers the feature amount extracted by the feature amount extraction unit as a feature amount of the person of interest, and an authentication unit which authenticates the person of interest in accordance with the similarity between the feature amount extracted by the feature amount extraction unit, and a feature amount which is registered by the dictionary registration unit.
1. A personal authentication system comprising:
a facial region extraction unit configured to extract images of a facial region of a person obtained from an image sensing input unit;
a guide unit configured to guide motion of the person of interest;
a feature amount extraction unit configured to extract a first feature amount of a face from a first image set of the facial region extracted by the facial region extraction unit;
a dictionary registration unit configured to register the first feature amount extracted by the feature amount extraction unit from the first image set extracted while the motion is guided by the guide unit as a feature amount of the person of interest; and
an authenticating unit configured to perform authentication using a second feature amount extracted at authentication from a second image extracted by the facial region extraction unit without guided motion and comparing said another second feature amount with the first feature amount extracted from the first image set extracted during guided motion and stored in the dictionary registration unit.
2. An apparatus according to claim 1 , further comprising:
an image sensing condition extraction unit configured to extract an image sensing condition on the basis of a size or luminance of the facial region extracted by the facial region extraction unit, and
wherein the guide unit guides the motion of the person of interest so that the image sensing condition extracted by the image sensing condition extraction unit falls within a predetermined value range.
3. An apparatus according to claim 1 , wherein the guide unit guides the motion of the person of interest by presenting a character which relaxes the person of interest upon registration or authentication.
4. An apparatus according to claim 1 , wherein the guide unit displays the facial image of a person to be authenticated, which is sensed upon dictionary registration or personal authentication, on a monitor, and guides the person to be authenticated on the basis of displayed contents.
5. An apparatus according to claim 1 , wherein the guide unit guides a person to be authenticated by displaying a character.
6. A personal authentication method comprising:
extracting a first image set of a facial region of a person obtained from an image sensing input means while motion is guided;
extracting a first feature amount of a face from the extracted first image set of the facial region;
registering the first feature amount extracted by the extracting a first feature amount as a feature amount of the person of interest;
second extracting a second image of a facial region of a person obtained from the image sensing input means without guided motion at an authentication; and
extracting a second feature amount of the facial region of the person obtained from the second image extracted from the sensing input means at the authentication; and
authenticating a person based on comparing said second feature amount with the registered first feature amount extracted from the first image set extracted during guided motion.
7. A method according to claim 6 , further comprising:
extracting an image sensing condition on the basis of a size or luminance of the facial region extracted in the guide step, and
wherein the guide step includes a step of guiding the motion of the person of interest so that the image sensing condition extracted in the image sensing condition extraction step falls within a predetermined value range.
8. A method according to claim 6 , wherein the guide step includes a step of guiding the motion of the person of interest by presenting a character which relaxes the person of interest upon registration or authentication.
9. A method according to claim 6 , wherein the guide step includes a step of displaying the facial image of a person to be authenticated, which is sensed upon dictionary registration or personal authentication, on a monitor, and guiding the person to be authenticated on the basis of displayed contents.
10. A method according to claim 6 , wherein the guide step includes a step of guiding a person to be authenticated by displaying a character.