Abstract:
A system receives an iris image and segments the iris region. The segmented iris region is mapped to a unit disk and partitioned into local iris regions (or sectors) as a function of the radius and angle The system calculates localized Zernike moments for a plurality of regions of the unit disk. The localized Zernike moment includes a projection of the local iris region into a space of Zernike polynomial orthogonal basis functions. The system generates an iris feature set from the localized Zernike moments for each partitioned region, excluding the regions which are comprised by occlusion. The iris features are weighted based on the conditions of blur, gaze and occlusion of the iris region. A probe iris image is then matched to a plurality of iris images in a database based on the distance of its feature set to the corresponding plurality of iris feature sets.
Abstract:
Image acquisition systems are described herein. One image acquisition system includes an image recording device configured to determine and record a tracking error associated with a raw image of a moving subject, and a computing device configured to deblur the raw image using the tracking error.
Abstract:
An image acquisition system that includes a first image recording device that records a series of images of a subject. A lateral velocity vector estimator receives the series of images from the first image recording device and estimates the lateral velocity vectors of the subject relative to the image acquisition system. The image acquisition system further includes a second image recording device that includes an orthogonal transfer CCD sensing element which records a target image of the subject. The orthogonal transfer CCD sensing element includes an array of pixels. A control adjusts the array of pixels within the orthogonal transfer CCD sensing element based on the lateral velocity vector estimates provided by the lateral velocity estimator.
Abstract:
A smoke detector includes processing circuitry coupled to a camera. The field of view of the camera contains one or more targets, each having spatial indicia thereon. The processing circuitry collects a sequence of spatial frequency measures, such as contrast indicating parameters. Members of the sequence can be compared to at least one reference spatial frequency measure to establish the presence of smoke between the target and the camera.
Abstract:
Image acquisition systems are described herein. One image acquisition system includes an image recording device configured to determine and record a tracking error associated with a raw image of a moving subject, and a computing device configured to deblur the raw image using the tracking error.
Abstract:
A swept distance between a subject and a plurality of cameras provides a plurality of raw images. Focused portions of the raw images are fused to generate a synthetic image and a distance image. A projection of the synthetic image and the distance image yields a panoramic image.
Abstract:
Devices and approaches for addressing wavefront corruption in biometric applications. A biometric imaging system may have a laser, a wavefront sensor, and an optical system. The laser may be configured to project a laser spot onto a skin portion of a human face, and the optical system may be configured to collect scattered light from the laser spot and relay the light to the wavefront sensor. The biometric imaging system may also have an adaptive optical element and a controller configured to provide actuation commands to the adaptive optical element based at least in part upon a wavefront distortion measurement output from the wavefront sensor. The optical system may further be configured to relay image light to an image camera of the optical system. The image camera may be an iris camera configured for obtaining iris images suitable for biometric identification.
Abstract:
A trending system and method for trending data in a mechanical system is provided. The trending system includes a sliding window filter. The sliding window filter receives a data set of data points generated by the mechanical system. The sliding window filter partitions the data set into a plurality of data windows, and uses the data windows to calculate upper and lower confidence bounds for the data set. Specifically, the sliding window filter calculates an upper confidence bounds and lower confidence bounds for each data point using each of the multiple data windows that includes the data point. The sliding window filter then selects the upper confidence bounds and the lower confidence bounds that results in the smallest mean prediction confidence interval for that data point. This results in a smoothed estimated trend for the data set that can be used for prognostication and fault detection.
Abstract:
A camera system may be used to capture iris images of targeted people who may be unaware of being targeted and hence their movement may not be constrained in any way. Iris images may be used for identification and/or tracking of people. In one illustrative embodiment, a camera system may include a focus camera and an iris camera, where the focus camera is sensitive to ambient light or some spectrum thereof, and the iris camera is sensitive to infrared or some other wavelength light. The focus camera and the iris camera may share an optical lens, and the focus camera may be used to auto-focus the lens on a focus target. A beam splitter or other optical element may be used to direct light of some wavelengths to the focus camera for auto-focusing the lens, and other wavelengths to the iris camera for image capture of the iris images.
Abstract:
A trending system and method for trending data in a mechanical system is provided. The trending system includes a sliding window filter. The sliding window filter receives a data set of data points generated by the mechanical system. The sliding window filter partitions the data set into a plurality of data windows, and uses the data windows to calculate upper and lower confidence bounds for the data set. Specifically, the sliding window filter calculates an upper confidence bounds and lower confidence bounds for each data point using each of the multiple data windows that includes the data point. The sliding window filter then selects the upper confidence bounds and the lower confidence bounds that results in the smallest mean prediction confidence interval for that data point. This results in a smoothed estimated trend for the data set that can be used for prognostication and fault detection.