Google Inc.

Carnegie Mellon University

Other

Pittsburgh Pattern Recognition, Inc.

Henry Will Schneiderman

Michael Andrew Sipe

Michael Nechyba

Yong Zhao

Steven Ross

Hugo Botelho Barra

Marco Paglia

Mikkel Crone Köser

Uriel Gerardo Rodriguez

Louis D Brandy

Takeo Kanade

Brian Patrick Williams

Christian Robertson

Rachel Leah Garb

Helena Roeber

A content annotation tool is disclosed. In a configuration, a portion of a movie may be obtained from a database. Entities, such as an actor, background music, text, etc. may be automatically identified in the movie. A user, such as a content producer, may associate and/or provide supplemental content for an identified entity to the database. A selection of one or more automatically identified entities may be received. A database entry may be generated that links the identified entity with the supplemental content. The selected automatically identified one or more entities and//or supplemental content associated therewith may be presented to an end user.

Content annotation tool

System and method for determining a classifier to discriminate between two classes&#x2014;object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image. The overall classifier is constructed of a sequence of classifiers, where each such classifier is based on a ratio of two graphical probability models. A discreet-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect different types of 3D objects. Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations belong to the same category.

Object recognizer and detector for two-dimensional images using Bayesian network based classifier

A method for dynamic switching of user profiles on a computing device. The computing device is coupled to at least one image-sensing device and can be configured using a plurality of stored user profiles. The method includes receiving at least one image from the at least one image-sensing device and generating a current user value based on the at least one received image. The method further includes determining if the current user value corresponds to at least one stored user value corresponding to a stored user profile. If the current user value corresponds to at least one stored user value, the method includes retrieving the stored user profile and configuring at least some programs operating on the computing device using the retrieved user profile. If the current user value does correspond to at least one stored user value, the method includes configuring the computing device using an alternative method.

Dynamic profile switching based on user identification

Supplemental information to a media content such as a video can be shown to the user. The supplemental information can be selected based upon a profile of the user and one or both of the identity of the media content and the identity of an entity of interest in the media content. The supplemental information can be customized to the user based on the content being viewed and an entity of interest to the user in the viewed content.

Rendering supplemental information concerning a scheduled event based on an identified entity in media content

Facial recognition can be used to determine whether or not a user has access privileges to a device such as a smartphone. It may be possible to spoof an authenticated user's image using a picture of the user. Implementations disclosed herein utilize time of flight and/or reflectivity measurements of an authenticated user to compare to such values obtained for an image of an object. If the time of flight distance and/or reflectivity distance for the object match a measured distance, then the person (i.e., object) may be granted access to the device.

Differentiating real faces from representations

A content annotation tool is disclosed. In a configuration, a portion of a movie may be obtained from a database. Entities, such as an actor, background music, text, etc. may be automatically identified in the movie. A user, such as a content producer, may associate and/or provide supplemental content for an identified entity to the database. A selection of one or more automatically identified entities may be received. A database entry may be generated that links the identified entity with the supplemental content. The selected automatically identified one or more entities and/or supplemental content associated therewith may be presented to an end user.

An example method includes capturing, by an image capture device of a computing device, an image of a face of a user. The method further includes detecting, by the computing device, whether a distance between the computing device and an object represented by at least a portion of the image is less than a threshold distance, and, when the detected distance is less than a threshold distance, denying authentication to the user with respect to accessing one or more functionalities controlled by the computing device, where the authentication is denied independent of performing facial recognition based at least in part on the captured image.

Facial recognition

An example method includes receiving a first image and a second image of a face of a user, where one or both images have been granted a match by facial recognition. The method further includes detecting a liveness gesture based on at least one of a yaw angle of the second image relative to the first image and a pitch angle of the second image relative to the first image, where the yaw angle corresponds to a transition along a horizontal axis, and where the pitch angle corresponds to a transition along a vertical axis. The method further includes generating a liveness score based on a yaw angle magnitude and/or a pitch angle magnitude, comparing the liveness score to a threshold value, and determining, based on the comparison, whether to deny authentication to the user with respect to accessing one or more functionalities controlled by the computing device.

A computing device includes an image capture device, a display, and at least one processor. The image capture device is configured to capture a digital enrollment image of a face of an authorized user and a digital authentication image of a face of an authenticating user. The display is configured to present the enrollment and authentication images. The at least one processor is configured to automatically alter the authentication image for presentation by the display and compare the authentication image to the enrollment image to unlock the computing device for use by the authenticating user.

Growing community of inventors

Pittsburgh, PA, United States of America

Henry Will Schneiderman