Abstract: A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.

Abstract: An image reproducing apparatus that achieves a higher readiness, high-speed backward reproduction, and a minimum amount of data, at a time of executing a backward reproduction. An encoder-side intra predictor transcodes decode images of a front end and a back end of a GOP of an image stream. An encoder-side motion compensator transcodes a decode image other than that of the front end of the GOP of the image stream by setting a motion vector to 0 and using an immediately preceding reference image.

Abstract: A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.

Abstract: A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.

Abstract: A plurality of iris codes are registered for each registrant in an iris database (12) together with pupil diameter-iris diameter ratio R. At the time of authentication, an iris code is obtained from a captured iris image by feature extraction while pupil diameter-iris diameter ratio R is obtained. Ratio R obtained at the time of registration and ratio R obtained at the time of authentication are compared to specify an appropriate iris code from the iris database (12) as an item to be collated before authentication.

Abstract: Image data of an image including an eye is input (S1), and band limitation is performed (S2). Then, a predetermined feature such as moment is extracted from the band-limited image data (S3), and recognition as to whether the eye projected in the image is a counterfeit eye or a living eye is performed based on the extracted feature (S4).

Abstract: A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.

Abstract: A plurality of iris images are acquired (SA0), and aggregation of iris images of which distribution of pupil openings is uniform is acquired from the plurality of iris images by duplication and/or deletion (SA1). Features are generated from the respective iris images that belong to the aggregation (SA2), and a predetermined number of registration features are selected from the features, using authentication performance as an evaluation index.

Abstract: In iris authentication, iris regions are extracted from a plurality of images (2a, 2b). The extracted iris regions are subjected to polar coordinate transformation (3a, 3b) and band limitation (4a, 4b). Thereafter, an iris code is generated from the coordinate-transformed, band-limited iris regions (5a, 5b). The iris code is subjected to rotational compensation (6a, 6b). A plurality of resultant iris codes are synthesized into a single iris code by determining the bit value of each bit based on a majority rule (7a, 7b).

Abstract: An eye image taking device comprises: an imaging unit for taking an eye of a user as an eye image; a focusing degree calculating unit for calculating the magnitude of high-frequency components from the eye image; a threshold setting unit for setting a focusing threshold intrinsic to an authorized user; and a focus deciding unit for deciding a focus by comparing the magnitude of the high-frequency components and the focusing threshold, so that the optimum focusing threshold is set for the authorized user.

Abstract: A plurality of images that include the same eye is input (S11) and iris regions are extracted therefrom to obtain iris images (S12). After the plural iris images are subjected to transformation from a rectangular coordinate system to a polar coordinate system (S13) and rotational compensation (S14), the images are added together while a weight is attached to a pixel value in each coordinate of the polar coordinate system, to accumulate them as a single iris image (S15). An iris code is generated from the thus obtained single iris image (S16, S17).

Abstract: Pupil candidate detection unit for detecting positions of pupil candidates in an eye image; and luminance difference calculation unit for obtaining a difference between a maximum value and a minimum value of an image data of an eye image on a circumference of a circle having a center at center coordinates of a pupil candidate and a predetermined radius are provided, and when the output of luminance difference calculation unit is larger than the predetermined threshold, the corresponding pupil candidate is determined not to be the pupil.

Abstract: An eye image taking device comprises: an imaging unit for taking the eye of a person to be authenticated, as an eye image; an illumination unit for illuminating the eye of the person to be authenticated; an eyeglass reflection detecting unit for detecting an eyeglass reflection from the eye image; and an instruction unit for instructing the person to be authenticated the movement of the imaging unit or the direction of the face of the person to be authenticated, in case an eyeglass reflection detecting portion detects the eyeglass reflection.

Abstract: A pupil detection device according to the present invention includes an image data extraction unit (220) for setting a plurality of concentric circles on an eye image respectively as integrating circle, and extracting the eye image data along the integrating circle, a contour integrating unit for integrating the image data along a circumference of the integrating circle and a pupil position detection unit for detecting center coordinates of the integrating circle whose integrated value obtained by the contour integrating unit changes stepwise with respect to the radius of the integrating circle as pupil position coordinates, and the image data extraction unit (220) includes a plurality of line memories (2241-224L) which can be accessed randomly and a plurality of selectors (2281-228n) for switching image data read from the line memories (2241-224L) in sequence and selecting image data corresponding to the respective integrating circles.

Abstract: A pupil candidate detection unit for detecting positions of pupil candidates which may be candidates of a pupil in an eye image; a pupil candidate retention unit for retaining a plurality of detected positions of the pupil candidates; and a pupil selection unit for selecting a pupil candidate, out of the plurality of pupil candidates, which includes center positions of other pupil candidates in an area within a predetermined distance from the center position of its own are provided.

Abstract: Pupil candidate detection unit for detecting positions of pupil candidates in an eye image; and luminance difference calculation unit for obtaining a difference between a maximum value and a minimum value of an image data of an eye image on a circumference of a circle having a center at center coordinates of a pupil candidate and a predetermined radius are provided, and when the output of luminance difference calculation unit is larger than the predetermined threshold, the corresponding pupil candidate is determined not to be the pupil.

Abstract: A pupil detection device includes an image data extraction unit for determining a plurality of concentric circles on an eye image respectively as integrating circles; a contour integrating unit for integrating the image data extracted by the image data extraction unit along the respective circumferences of the integrating circles; a pupil radius detection unit for detecting that the integrated value of the integrating circle has changed stepwise; a pupil position detection unit for detecting that the center coordinates of the integrating circle as pupil position coordinates when the integrated value of the integrating circle is changed stepwise with respect to the radius of the integrating circle, and the image data extraction unit extracts a plurality of image data simultaneously.

Abstract: According to the present invention, when an image data currently being received is switched over to the data from another image information device, the best picture quality is provided without stopping the image up to the next I frame even when the switching request is given at the middle of I frame.

Abstract: An eye-imaging device and a portable terminal device using the same can take eye-images keeping a certain distance between the subject person's eye and camera. The eye-imaging device includes: an imager capable of switching over between a telephoto mode to take eye-images and a wide-angle mode to take facial images of a subject person, keeping a certain distance between the subject person's eye and camera; a display to display images taken by the wide-angle mode; a guide checker to check automatically that the eye has been guided to a predetermined position according to the image taken by the wide-angle mode; and a lens selector to switch over the imager automatically from the wide-angle mode to the telephoto mode when the guide checker checks that the eye has been guided to the predetermined position.

Abstract: A plurality of images that include the same eye is input (S11) and iris regions are extracted therefrom to obtain iris images (S12). After the plural iris images are subjected to transformation from a rectangular coordinate system to a polar coordinate system (S13) and rotational compensation (S14), the images are added together while a weight is attached to a pixel value in each coordinate of the polar coordinate system, to accumulate them as a single iris image (S15). An iris code is generated from the thus obtained single iris image (S16, S17).