Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: A biometric authentication platform (10) uses fault-tolerant distributed computing to determine if a supplied biometric sample and a sample stored in a registry are from the same person. A collection of reference samples is maintained in a distributed ledger (115) with immutable history of modifications. Results of matching are stored in a separate distributed ledger (125) providing an immutable history log. Coordinated use of both ledgers (115, 125) enable biometric authentication of registered users (140) in real time. Users (140) may interact with providers (150) and/or trusted circles of other users in order to recover user records from the user ledger (115).

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The invention presents a biometric authentication system comprising: a template module and a key module that are independent of each other. The template module is used to store encrypted biometric templates, the key module is used to store the decryption keys. The system may further comprise a matching module that acquires the decryption key from the key module and the encrypted template from the template module, decrypts the template using the key, then matches the template to verify the identity. In this system, the encrypted template and decryption key are stored separately both logically and physically, and are only united momentarily during matching, then are immediately deleted. The system is highly secure and addresses the security vulnerabilities in the current banking and payment systems, both online and offline such as ATM machines.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: A biometric authentication platform (10) uses fault-tolerant distributed computing to determine if a supplied biometric sample and a sample stored in a registry are from the same person. A collection of reference samples is maintained in a distributed ledger (115) with immutable history of modifications. Results of matching are stored in a separate distributed ledger (125) providing an immutable history log. Coordinated use of both ledgers (115, 125) enable biometric authentication of registered users (140) in real time. Users (140) may interact with providers (150) and/or trusted circles of other users in order to recover user records from the user ledger (115).

Abstract: A biometric authentication platform uses fault-tolerant distributed computing to determine if a supplied biometric live scan and template are from the same person. Features provide additional protection for biometric data. The template and live scan may be encrypted using a symmetric encryption key. The encrypted template and live scan may be sent with copies of the symmetric key, each copy further encrypted by a public key associated with one processor's public-private key pair. Each processor may decrypt a copy of the symmetric key, which may then be used by the processor for decrypting the live scan and template for matching. A decentralized user ledger may store an encrypted copy of the biometric template, with the key stored locally in a registered device. Alternatively, a decentralized user ledger may store a hash of the biometric template, for verification of a template that is maintained on a registered device.

Abstract: A biometric authentication platform uses fault-tolerant distributed computing to determine if a supplied biometric sample and a template sample, which may be stored in a registry, are from the same person. Samples may be subdivided and assigned to Sub-Sample Processing Clusters for processing in parallel to determine sub-results. A consensus authentication result may then be determined by the processing cluster based upon the sub-results.

Abstract: A biometric authentication platform (10) uses fault-tolerant distributed computing to determine if a supplied biometric sample and a sample stored in a registry are from the same person. A collection of reference samples may be maintained in a distributed user ledger (115), and results of matching are stored in a separate distributed authentication ledger (125). Coordinated use of both ledgers (115, 125) enable biometric authentication of registered users (140) in real time. Variations enable use of a user ledger (115) without an authentication ledger (125), and use of an authentication ledger (125) without a user ledger (115). Either or both ledgers (115, 125) may be shared, private, or combinations of shared and private. Secondary channel audits verify reliability of nodes within a network. Samples may be subdivided and processed in parallel. Sample encryption may be maintained for each processor in a node network.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: In at least one aspect, a method can include determining a location of a head mounted display (HMD) of a user, defining a location of a joint based on the location of the HMD, defining a segment from the joint to an end of the segment, defining an initial virtual location of a virtual controller within a virtual reality (VR) environment based on a location of the end of the segment, and defining a virtual location and a virtual orientation of the virtual controller within the VR environment, based on the segment and the joint, in response to an orientation movement of a physical controller.

Abstract: In at least one aspect, a method can include determining a location of a head mounted display (HMD) of a user, defining a location of a joint based on the location of the HMD, defining a segment from the joint to an end of the segment, defining an initial virtual location of a virtual controller within a virtual reality (VR) environment based on a location of the end of the segment, and defining a virtual location and a virtual orientation of the virtual controller within the VR environment, based on the segment and the joint, in response to an orientation movement of a physical controller.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

Abstract: The technology disclosed relates to initializing orientation of a three-dimensional (3D) model of an object. In particular, it relates to accessing at least one three-dimensional (3D) model of an object and observed information of the object movable in space and determining a primary orientation parameter of the model from the observed information. The method further includes detecting contours of the object in the observed information and calculating a representative normal to the detected contours, accessing a vector representing a 3D angle from the object to a point of observation, calculating a primary orientation of the object as a cross-product of the representative normal and the vector, and using the calculated primary orientation parameter to initialize the model.