Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.

Abstract: An image acquisition system for acquiring iris images for use in biometric recognition of a subject includes an optical system comprising a cluster of at least 2 lenses arranged in front of a common image sensor with each lens optical axis in parallel spaced apart relationship. Each lens has a fixed focus and a different aperture to provide a respective angular field of view. The lens with the closest focus has the smallest aperture and the lens with the farthest focus has the largest aperture so that iris images can be acquired across a focal range of at least from 200 mm to 300 mm.

Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.

Abstract: A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images arc processed based on the stereoscopic counterpart relationships to form a stereoscopic panorama image.

Abstract: A method of estimating motion between a pair of image frames of a given scene comprises calculating respective integral images for each of the image frames and selecting at least one corresponding region of interest within each frame. For each region of interest, an integral image profile from each integral image is calculated, each profile comprising an array of elements, each element comprising a sum of pixel intensities from successive swaths of the region of interest for the frame. Integral image profiles are correlated to determine a relative displacement of the region of interest between the pair of frames. Each region of interest is divided into a plurality of further regions of interest before repeating until a required hierarchy of estimated motion for successively divided regions of interest is provided.

Abstract: Systems and methods discussed herein can provide three-dimensional audio virtualization with sweet spot adaptation. In an example, an audio processor circuit can be used to update audio signals for sweet spot adaptation based on information from at least one depth sensor or camera about a listener position in a listening environment.

Abstract: A peripheral processing device comprises a physical interface for connecting the processing device to a host computing device through a communications protocol. A local controller connected to local memory across an internal bus provides input/output access to data stored on the processing device to the host through a file system API. A neural processor comprises at least one network processing engine for processing a layer of a neural network according to a network configuration. A memory at least temporarily stores network configuration information, input image information, intermediate image information and output information produced by each network processing engine. The local controller is arranged to receive network configuration information through a file system API write command, to receive input image information through a file system API write command; and to write output information to the local memory for retrieval by the host through a file system API read command.

Abstract: A hand-held or otherwise portable or spatial or temporal performance-based image capture device includes one or more lenses, an aperture and a main sensor for capturing an original main image. A secondary sensor and optical system are for capturing a reference image that has temporal and spatial overlap with the original image. The device performs an image processing method including capturing the main image with the main sensor and the reference image with the secondary sensor, and utilizing information from the reference image to enhance the main image. The main and secondary sensors are contained together within a housing.

Abstract: A method operable by a computing device for configuring access for a limited user interface (UI) device to a network service via a local network access point is disclosed. The method comprises the steps of: obtaining from the limited UI device a device identifier via a first out-of-band channel. The device identifier is provided to the network service via a secure network link. A zero knowledge proof (ZKP) challenge is received from the network service. Configuration information is provided to the limited-UI device via a second out-of-band channel, the configuration information including information sufficient to enable the limited-UI device to connect to the local network access point. The ZKP challenge is provided to the limited-UI device via the second out-of-band channel.

Abstract: An optical system for an image acquisition device comprises a filter comprising a central aperture arranged to transmit both visible and selected near infra-red (NIR) wavelengths and a peripheral aperture arranged to block visible wavelengths and to transmit the NIR wavelengths. An image sensor comprises an array of pixels including pixels sensitive to visible wavelengths and corresponding pixels sensitive to the NIR wavelengths. A lens assembly is axially located between the filter and the image sensor and comprises a plurality of lens elements. The lens elements are arranged to simultaneously focus NIR light received from a given object through central and peripheral apertures of the filter and visible light received from the object through the central aperture onto the sensor surface.

Abstract: A computer-implemented method for viewing images on an interactive computing device comprises displaying an image from a stack comprising a display image and at least one compressed sub-image of nominally the same scene, each of the sub-images of the stack having been acquired at respective focal distances. Responsive to a user selecting a portion of the displayed image, the selected portion is mapped to a corresponding mapped portion of a sub-image within the stack according to the difference in focal distances between the displayed image and the sub-image. At least one row of compressed image blocks of the at least one sub-image extending across the mapped portion; and a reference value for a point in the compressed image stream of the sub-image preceding the row of compressed image blocks is determined.

Abstract: A method for calibrating an image capture device comprises mounting at least one sample device from a batch for movement through a plurality of orientations relative to a horizontal plane. For a given orientation, the sample device is focused at a sequence of positions, each position being at a respective focus distance from the device. A lens actuator setting is recorded for the sample device at each position. This is repeated at a plurality of distinct orientations of the sample device. Respective relationships are determined between lens actuator settings at any given position for distinct orientations from the plurality of distinct orientations and actuator settings at a selected orientation of the plurality of distinct orientations. Lens actuator settings for the image capture device to be calibrated are recorded at least at two points of interest (POI), each a specified focus distance from the device with the image capture device positioned at the selected orientation.

Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.

Abstract: A hand-held digital image capture device (digital camera) has a user-selectable mode in which upon engaging the mode the device detects a face in the field of view of the device and generates a face delimiter on a camera display screen, the delimiter surrounding the initial position of the image of a the face on the screen. The device is arranged to indicate thereafter to the user if the device departs from movement along a predetermined concave path P with the optical axis of the device pointing towards the face, such indication being made by movement of the image of the face relative to the delimiter. The camera captures and stores a plurality of images at successive positions along the concave path.

Abstract: A method and system for detecting facial expressions in digital images and applications therefore are disclosed. Analysis of a digital image determines whether or not a smile and/or blink is present on a person's face. Face recognition, and/or a pose or illumination condition determination, permits application of a specific, relatively small classifier cascade.

Abstract: A technique of generating a stereoscopic panorama image includes panning a portable camera device, and acquiring multiple image frames. Multiple at least partially overlapping image frames are acquired of portions of the scene. The method involves registering the image frames, including determining displacements of the imaging device between acquisitions of image frames. Multiple panorama images are generated including joining image frames of the scene according to spatial relationships and determining stereoscopic counterpart relationships between the multiple panorama images. The multiple panorama images are processed based on the stereoscopic counterpart relationships to form a stereoscopic panorama image.

Abstract: A method operable by a computing device for configuring access for a limited user interface (UI) device to a network service via a local network access point is disclosed. The method comprises the steps of: obtaining from the limited UI device a device identifier via a first out-of-band channel. The device identifier is provided to the network service via a secure network link. A zero knowledge proof (ZKP) challenge is received from the network service. Configuration information is provided to the limited-UI device via a second out-of-band channel, the configuration information including information sufficient to enable the limited-UI device to connect to the local network access point. The ZKP challenge is provided to the limited-UI device via the second out-of-band channel.

Abstract: Systems and methods for utilizing payment card information stored on a secure biometric processor on a mobile device in accordance with various embodiments of the invention are disclosed. In one embodiment, a process for securely providing payment card information from a portable device to a payment terminal includes receiving a request for payment using a payment interface, triggering a user authentication by capturing a set of biometric information from one or more biometric sensors, calculating, using the captured set of biometric information, a match with a set of stored biometric information that is stored on a secure biometric processor in order to determine a user identifier of an authenticated user, determining a payment card out of a set of payment cards associated with the user identifier, retrieving payment card information for the determined payment card from the secure biometric processor, and transmitting the payment card information to a payment terminal.

Abstract: A rearview imaging system for a vehicle includes at least one video camera mounted at the rear of the vehicle for providing a wide angle horizontal field of view (FoV) rearwardly of the vehicle, and a display device in the vehicle at a position viewable by the driver. A video processor subdivides the camera FoV into three horizontally disposed sub-FOVs and displaying said sub-FoVs on visually separated side-by-side regions of the display device screen. The horizontal position and/or extent of at least one sub-FoV is variable as a function of the motion of the vehicle.

Abstract: A method of generating a digital video image uses a wide-angle field of view (WFOV) lens positioned closely in front of an image sensor array so that the image field of the lens is so curved at the sensor array that different regions of the image field are substantially in focus on the sensor array for different positions of the lens. The method comprises selecting a desired region of interest in the image field of the lens, and adjusting the lens/array distance to bring the region of interest into focus on the sensor array. The in-focus region of interest is stored and at least partially corrected for field-of-view distortion due to the WFOV lens. The corrected image is displayed, locally and/or remotely. These steps are cyclically repeated to provide the video image.