Abstract: In one aspect, a first device includes at least one processor and storage with instructions executable by the processor to receive input from a camera and to identify, based on the input from the camera, a first lighting condition of a scene showing a user. Responsive to the first lighting condition satisfying a first criterion, the instructions are executable to transmit a first video stream showing the user's face as captured by the camera to a second device. Responsive to the first lighting condition not satisfying the first criterion, the instructions are executable to use a model to generate a 3D representation of the user's face according to one or more parameters related to the user and to transmit a second video stream to the second device that shows the 3D representation. The model is also trained under lighting conditions satisfying one or more criteria.

Abstract: An approach is provided that uses augmented/virtual reality to identify occupied meeting rooms. The approach captures, at a digital camera, a digital image of an exterior of a closed-door meeting room. The meeting room in the digital image is identified and a set of data pertaining to the identified meeting room is retrieved. The set of data indicates whether the meeting room is currently occupied. The captured digital image is displayed on a display screen with an overlay of the retrieved set of data indicating whether the meeting room is currently occupied.

Abstract: A noise filtering engine and method that removes fixed and random pattern noise from a digital image source. The engine may be implemented, for example, as a subsystem of a hardware-based pipeline for digital image processing or in software or a combination of hardware and software. The noise reduction engine consists of one or more hardware blocks to facilitate high throughout and high-performance operations. The engine has a significant degree of flexibility and programmability allowing, for example, digital camera manufacturers to implement the noise reduction engine in medium to high-end cameras operating with various types of imagers including CCD and CMS image sensors.

Abstract: A lens vignetting correction method for use in imaging systems such as digital cameras employs a polynomial correction function F=ar2+br4+c, wherein r is a distance to a center of correction. A calibration image is obtained using the imaging system, then the correction function applied to the calibration image is least-squares fit to determine the variable coefficients a, b and c. Subsequent raw images from this imaging system are corrected by applying the correction function thereto on a pixel-by-pixel basis. A recursive technique is used to obtain correction function values for given pixel locations from modification of values for preceding pixel locations.

Abstract: A method and system for providing an application specific integrated circuit (ASIC) for a digital image processing system is disclosed. The method and system include providing a microprocessor subsystem and providing an image processing subsystem. The microprocessor subsystem controls the digital image processing system. The image processing subsystem includes image processing hardware and programmable logic. The programmable logic includes a plurality of programmable cells that are customized during fabrication of the ASIC.