Abstract: A face authentication or recognition system embodiment includes a processing unit; a flash illumination drive circuit; a flash illumination unit having a flashlamp configured to generate a set of flash illumination pulses; a set of spectral filters configured to pass a set of spectrally filtered flash illumination pulses; a lens; an image sensor configured to receive a set of filtered flash illumination pulses reflected from a subject's face and generate a corresponding facial image dataset; and a memory or data storage device configured to store facial image datasets, enrollment datasets, and query datasets, and which includes a face authentication or recognition module. Spectrally filtered flash illumination pulses have an intensity at least approximately equal to the intensity of ambient sunlight, essentially regardless of an outdoor environment under consideration upon or proximate to the surface of the earth.

Abstract: A face authentication or recognition system embodiment includes a processing unit; a flash illumination drive circuit; a flash illumination unit having a flashlamp configured to generate a set of flash illumination pulses; a set of spectral filters configured to pass a set of spectrally filtered flash illumination pulses; a lens; an image sensor configured to receive a set of filtered flash illumination pulses reflected from a subject's face and generate a corresponding facial image dataset; and a memory or data storage device configured to store facial image datasets, enrolment datasets, and query datasets, and which includes a face authentication or recognition module. Spectrally filtered flash illumination pulses have an intensity at least approximately equal to the intensity of ambient sunlight, essentially regardless of an outdoor environment under consideration upon or proximate to the surface of the earth.

Abstract: A system and method for capturing an image for biometric identification. To obtain the image, a person stands or moves in a target zone. A flash element provides an incoherent flash of light through an aperture. The flash is filtered to produce filtered light. The filtered light has primary wavelengths no longer than that of blue light. The filtered light is not perceived well by the human eye due to its short duration, color and small point of origin. The intensity of the filtered light at the target area surpasses the intensity of all ambient light. In this manner, a person in the target area will always be properly illuminated, even if that person were backlit by full sunlight. An image of the person is taken with a camera. The image is analyzed to obtain any biometric patterns that can be used for identification.

Abstract: A system and method for capturing an image for biometric identification. To obtain the image, a person stands or moves in a target zone. A flash element provides an incoherent flash of light through an aperture. The flash is filtered to produce filtered light. The filtered light has primary wavelengths no longer than that of blue light. The filtered light is not perceived well by the human eye due to its short duration, color and small point of origin. The intensity of the filtered light at the target area surpasses the intensity of all ambient light. In this manner, a person in the target area will always be properly illuminated, even if that person were backlit by full sunlight. An image of the person is taken with a camera. The image is analyzed to obtain any biometric patterns that can be used for identification.

Abstract: A system and method for capturing an image of one or both irises. To image an iris, a person stands or moves in a target zone. A flash element provides an incoherent flash of light through an aperture. The flash is filtered to produce filtered light. The filtered light has primary wavelengths in the far red and near infrared portions of the spectrum. The filtered light is not perceived well by the human eye due to short duration, NIR color and small size. The intensity of the filtered light at the target area surpasses the intensity of all ambient light. In this manner, a person's face in the target area will always be properly illuminated, even if that person were backlit by full sunlight. An image of the person's face is taken with a camera. The image of the face is analyzed to obtain any iris pattern information.

Abstract: A system and method for capturing an image of one or both irises. To image an iris, a person stands or moves in a target zone. A flash element provides an incoherent flash of light through an aperture. The flash is filtered to produce filtered light. The filtered light has primary wavelengths in the far red and near infrared portions of the spectrum. The filtered light is not perceived well by the human eye due to short duration, NIR color and small size. The intensity of the filtered light at the target area surpasses the intensity of all ambient light. In this manner, a person's face in the target area will always be properly illuminated, even if that person were backlit by full sunlight. An image of the person's face is taken with a camera. The image of the face is analyzed to obtain any iris pattern information.

Abstract: A system and method are disclosed for determining the pose angle of an object in an input image. In a preferred embodiment, the present system comprises a pose estimator having a prototype projector, a regression estimator, and an angle calculator. The prototype projector is preferably adapted to reduce the input image dimensionality for faster further processing by projecting the input pixels of the image onto a Self-Organizing Map (SOM) neural network. The regression estimator is preferably implemented as a neural network and adapted to map the projections to a pattern unique to each pose. The angle calculator preferably includes a curve fitter and an error analyzer. The curve fitter is preferably adapted to estimate the pose angle from the mapping pattern. The error analyzer is preferably adapted to produce a confidence signal representing the likelihood of the input image being a face at the calculated pose.

Abstract: A system and method are disclosed for determining the pose angle of an object in an input image. In a preferred embodiment, the present system comprises a pose estimator having a prototype projector, a regression estimator, and an angle calculator. The prototype projector is preferably adapted to reduce the input image dimensionality for faster further processing by projecting the input pixels of the image onto a Self-Organizing Map (SOM) neural network. The regression estimator is preferably implemented as a neural network and adapted to map the projections to a pattern unique to each pose. The angle calculator preferably includes a curve fitter and an error analyzer. The curve fitter is preferably adapted to estimate the pose angle from the mapping pattern. The error analyzer is preferably adapted to produce a confidence signal representing the likelihood of the input image being a face at the calculated pose.