Microsoft Technology Licensing, LLC

Other

Yichen Wei

Jian Qiao Sun

Jinyu Li

John R Lewis

Robert L Crocco, Jr

Benjamin Isaac Vaught

Kathryn Stone Perez

Alex Aben-Athar Kipman

Tommer Leyvand

Casey Leon Meekhof

Fang Wen

Mitchell Stephen Dernis

Timothy Milton Keosababian

Shahram Izadi

Michael John Conrad

Lu Yuan

Cem Keskin

Vladimir Tankovich

Jie Feng

Eric I-Chao Chang

Simon Stachniak

Zhuowen Tu

Chun-Te Chu

Junyan Zhu

Emad Barsoum

Tim Keosababian

Sean Ryan Francesco Fanello

Xudong Cao

Jifeng Dai

Shaoqing Ren

Litian Tao

Ben Butler

Aamir Jawaid

Jiajun Wu

Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.

Spoofed face detection

Various embodiments herein each include at least one of systems, methods, and software for feature flow for video recognition. Such embodiments generally include a fast and accurate framework for video recognition. One example method includes receiving a first frame captured by an imaging device and designating the first frame as a key frame. The method may then generate at least one feature map to identify features in the key frame and subsequently receive a second frame. The method also includes designating the second frame as a current frame and applying a flow estimation algorithm to the key frame and current frame to generate a flow field representing a flow from the key frame to the current frame. The method then propagates each of the at least one feature maps based on the flow field to approximate current locations of features identified within each of the at least one feature maps.

Feature flow for video recognition

The subject matter described herein relates to face alignment via shape regression. A method, computer storage medium, and system are provided. In one embodiment, the method comprises receiving an image including a face; and performing shape regression to estimate a facial shape in the image. For each stage in the shape regression, a local feature is extracted from a local region around each facial landmark in the image independently; and a joint projection is performed based on local features of multiple facial landmarks to predict a facial shape increment. Then, a facial shape of a current stage is generated based on the predicted facial shape increment and a facial shape of a previous stage.

Face alignment with shape regression

Disclosed herein are techniques and systems for computing geodesic saliency of images using background priors. An input image may be segmented into a plurality of patches, and a graph associated with the image may be generated, the graph comprising nodes and edges. The nodes of the graph include nodes that correspond to the plurality of patches of the image plus an additional virtual background node that is added to the graph. The graph further includes edges that connect the nodes to each other, including internal edges between adjacent patches and boundary edges between those patches at the boundary of the image and the virtual background node. Using this graph, a saliency value, called the 'geodesic' saliency, for each patch of the image is determined as a length of a shortest path from a respective patch to the virtual background node.

Geodesic saliency using background priors

A signal encoding an infrared (IR) image including a plurality of IR pixels is received from an IR camera. Each IR pixel specifies one or more IR parameters of that IR pixel. IR-skin pixels that image a human hand are identified in the IR image. For each IR-skin pixel, a depth of a human hand portion imaged by that IR-skin pixel is estimated based on the IR parameters of that IR-skin pixel. A skeletal hand model including a plurality of hand joints is derived. Each hand joint is defined with three independent position coordinates inferred from the estimated depths of each human hand portion.

Two-dimensional infrared depth sensing

A video game system (or other data processing system) can visually identify a person entering a field of view of the system and determine whether the person has been previously interacting with the system. In one embodiment, the system establishes thresholds, enrolls players, performs the video game (or other application) including interacting with a subset of the players based on the enrolling, determines that a person has become detectable in the field of view of the system, automatically determines whether the person is one of the enrolled players, maps the person to an enrolled player and interacts with the person based on the mapping if it is determined that the person is one of the enrolled players, and assigns a new identification to the person and interacts with the person based on the new identification if it is determined that the person is not one of the enrolled players.

Visual based identity tracking

Techniques for unsupervised object class discovery via bottom-up multiple class learning are described. These techniques may include receiving multiple images containing one or more object classes. The multiple images may be analyzed to extract top saliency instances and least saliency instances. These saliency instances may be clustered to generate and/or update statistical models. The statistical models may be used to discover the one or more object classes. In some instances, the statistical models may be used to discover object classes of novel images.

Unsupervised object class discovery via bottom up multiple class learning

The technology provides for automatic alignment of a see-through near-eye, mixed reality device with an inter-pupillary distance (IPD). A determination is made as to whether a see-through, near-eye, mixed reality display device is aligned with an IPD of a user. If the display device is not aligned with the IPD, the display device is automatically adjusted. In some examples, the alignment determination is based on determinations of whether an optical axis of each display optical system positioned to be seen through by a respective eye is aligned with a pupil of the respective eye in accordance with an alignment criteria. The pupil alignment may be determined based on an arrangement of gaze detection elements for each display optical system including at least one sensor for capturing data of the respective eye and the captured data. The captured data may be image data, image and glint data, and glint data only.

Aligning inter-pupillary distance in a near-eye display system

Systems, methods, and computer media for estimating user eye gaze are provided. A plurality of images of a user's eye are acquired. At least one image of at least part of the user's field of view is acquired. At least one gaze target area in the user's field of view is determined based on the plurality of images of the user's eye. An enhanced user eye gaze is then estimated by narrowing a database of eye information and corresponding known gaze lines to a subset of the eye information having gaze lines corresponding to a gaze target area. User eye information derived from the images of the user's eye is then compared with the narrowed subset of the eye information, and an enhanced estimated user eye gaze is identified as the known gaze line of a matching eye image.

Enhanced user eye gaze estimation

The technology provides various embodiments for gaze determination within a see-through, near-eye, mixed reality display device. In some embodiments, the boundaries of a gaze detection coordinate system can be determined from a spatial relationship between a user eye and gaze detection elements such as illuminators and at least one light sensor positioned on a support structure such as an eyeglasses frame. The gaze detection coordinate system allows for determination of a gaze vector from each eye based on data representing glints on the user eye, or a combination of image and glint data. A point of gaze may be determined in a three-dimensional user field of view including real and virtual objects. The spatial relationship between the gaze detection elements and the eye may be checked and may trigger a re-calibration of training data sets if the boundaries of the gaze detection coordinate system have changed.

Gaze detection in a see-through, near-eye, mixed reality display

A computing device configured to determine, for each of a plurality of locations in an image, a saliency measure based at least on a cost of composing parts of the image in the location from parts of the image outside of the location is described herein. The computing device is further configured to select one or more of the locations as representing salient objects of the image based at least on the saliency measures.

Salient object detection by composition

Visual based identitiy tracking

Methods are provided for generating a low dimension pose space and using the pose space to estimate one or more head rotation angles of a user head. In one example, training image frames including a test subject head are captured under a plurality of conditions. For each frame an actual head rotation angle about a rotation axis is recorded. In each frame a face image is detected and converted to an LBP feature vector. Using principal component analysis a PCA feature vector is generated. Pose classes related to rotation angles about a rotation axis are defined. The PCA feature vectors are grouped into a pose class that corresponds to the actual rotation angle associated with the PCA feature vector. Linear discriminant analysis is applied to the pose classes to generate the low dimension pose space.

Real time head pose estimation

Growing community of inventors

Beijing, China

Yichen Wei