Microsoft Technology Licensing, LLC

Zhigu Holdings Limited

Qin Cai

Zhengyou Zhang

Zicheng Liu

Anoop Gupta

Michael John Conrad

Qing Zhang

Pieter Kasselman

Arthur Baker

Dijia Wu

Xu Miao

Tim Burrell

Jia-Bin Huang

Aswin Sankaranarayanan

John Hamaker

Zhengyu Zhang

Pieter R Kasselman

Arthur H Baker

The subject disclosure is generally directed towards eye gaze detection based upon both eyes being fixated on the same gaze location. In one aspect, an image including a subject's left and right eyes is captured, from which left and right glint and pupil center information are extracted. The left and right glint data and the left and right pupil data are used with left and right bias correction matrices to jointly determine a gaze location.

Eye gaze tracking using binocular fixation constraints

Examples are disclosed herein that are related to gaze tracking via image data. One example provides, on a gaze tracking system comprising an image sensor, a method of determining a gaze direction, the method comprising acquiring image data via the image sensor, detecting in the image data facial features of a human subject, determining an eye rotation center based upon the facial features using a calibrated face model, determining an estimated position of a center of a lens of an eye from the image data, determining an optical axis based upon the eye rotation center and the estimated position of the center of the lens, determining a visual axis by applying an adjustment to the optical axis, determining the gaze direction based upon the visual axis, and providing an output based upon the gaze direction.

Gaze tracking via eye gaze model

The subject disclosure is directed towards eye gaze detection based upon multiple cameras and/or light sources along with an adaptive homography mapping model. Learning of the model includes compensating for spatially-varying gaze errors and head pose dependent errors simultaneously in a unified framework. Aspects including training the model of adaptive homography offline using simulated data at various head positions.

Eye gaze tracking based upon adaptive homography mapping

The subject disclosure is directed towards eye gaze detection based upon multiple cameras and/or light sources. The cameras and/or light sources are configured to provide eye gaze detection for a device display at different orientations, at different tilt angles, at different user positions, at different user distances, and so on. Also described is a controller that selectively controls light source power and camera on/off state to provide images of the eye having sufficient quality for eye gaze detection and/or to conserve power.

Eye gaze detection with multiple light sources and sensors

Multiple images including a face presented by a user are accessed. One or more determinations are made based on the multiple images, such as a determination of whether the face included in the multiple images is a 3-dimensional structure or a flat surface and/or a determination of whether motion is present in one or more face components (e.g., eyes or mouth). If it is determined that the face included in the multiple images is a 3-dimensional structure or that that motion is present in the one or more face components, then an indication is provided that the user can be authenticated. However, if it is determined that the face included in the multiple images is a flat surface or that motion is not present in the one or more face components, then an indication is provided that the user cannot be authenticated.

Distinguishing live faces from flat surfaces

A multi-party spatial audio conferencing system is configured to receive far end signals from remote participants. The system comprises a speaker array that outputs spatialized sound signals and one or more microphones that capture and relay a sound signal comprising an echo of the spatialized sound signal to a multichannel acoustic echo cancellation (MC-AEC) unit having a plurality of echo cancellers. Respective echo cancellers perform cancellation of an echo associated with a far end signal from one of the multiple participants according to an algorithm based upon echo cancellation coefficients. The echo cancellation coefficients are determined from the input channel signals, the spatialization parameters associated with each input channel, and the audio signals captured by the microphones. This allows respective echo cancellation filters to be updated simultaneously even though the corresponding remote participant is not talking.

Multichannel acoustic echo cancellation

Techniques and technologies for tracking a face with a plurality of cameras wherein a geometry between the cameras is initially unknown. One disclosed method includes detecting a head with two of the cameras and registering a head model with the image of the head (as detected by one of the cameras). The method also includes back projecting the other detected face image to the head model and determining a head pose from the back-projected head image. Furthermore, the determined geometry is used to track the face with at least one of the cameras.

Multi-camera head pose tracking

Architecture for testing an application grammar for the presence of confusable terms. A grammar confusability metric (GCM) is generated for describing a likelihood that a reference term will be confused by the speech recognizer with another term phrase currently allowed by active grammar rules. The GCM is used to flag processing of two phrases in the grammar that have different semantic meaning, but that the speech recognizer could have difficulty distinguishing reliably. A built-in acoustic model is analyzed and feature vectors generated that are close to the acoustic properties of the input term. The feature vectors are then sent for recognition. A statistically random sampling method is applied to explore the acoustic properties of feature vectors of the input term phrase spatially and temporally. The feature vectors are perturbed in the neighborhood of the time domain and the Gaussian mixture model to which the feature vectors belong.

Growing community of inventors

Clyde Hill, WA, United States of America

Qin Cai