Abstract: A method includes: normalizing intensities at each pixel in a fingerprint slap scan image such that variations of pixel intensities between fingerprint ridges and valleys are regularized; subsequently dividing the fingerprint slap scan image into blocks of pixels; for each block of pixels, estimating a spatial separation between adjacent fingerprint ridges as well as a ridge orientation for each fingerprint ridge within the particular block of pixels; calculating a distortion map for the various blocks by projecting, according to the estimated ridge orientation for each fingerprint ridge, an adjustment to the estimated spatial separation that is based on a difference between the estimated spatial separation and a target spatial separation; and warping the fingerprint slap scan image to compensate for the calculated distortion map such that the fingerprint ridges in the warped fingerprint slap scan image are scaled to compensate for local variations of adjustments in the calculated distortion map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for accessing information encoding an identification document of a subject. The identification document includes biometric information for the subject. A computing device determines that the identification document is authentic. In response to the device determining that the document is authentic, the device verifies the validity of personally identifiable information on the identification document. In response to a determination of validity, the device is used to obtain a live biometric of the subject. The obtained live biometric is compared with biometric information from the identification document that has been authenticated. In response to the comparison indicating a match, a system determines that the subject is the person identified by the identification document. The system extracts personally identifiable information from the identification document to register the subject.

Abstract: A machine-assisted method for verifying a video presence that includes: receiving, at a computing device of an identity provider, an authentication request initially sent from a requester to access an account managed by a relying party, different from the identity provider; retrieving, from the authentication request, at least a portion of a video stream feed initially from the requester, to the computing device, the portion of video stream feed portraying a face of the requester; extracting the face of the requester from the portion of the video stream feed; providing a directive to the requester soliciting a corresponding gesture; and receiving a response gesture from the requester.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shape detection are disclosed. In one aspect, a method includes the actions of generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation. The actions further include receiving an image. The actions further include identifying edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model. The actions further include selecting a plurality of edges that likely correspond to edges of a shape that is similar to the shape model. The actions further include determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model. The actions further include identifying a particular shape in the image that most closely fits the shape model.

Abstract: Some implementations may include a method for watermarking an identification document, the method including: modulating a spatial luminance pattern associated with a first digital watermark to encode a first portion of personally identifiable information; modulating a spatial chrominance distribution associated with a second digital watermark to encode a second portion of the personally identifiable information; and applying the first digital watermark and the second digital watermark to the identification document.

Abstract: In some implementations, a computer-implemented method and system for enrolling customers into a digital identification program may include obtaining, from a digital identification database, customer information that describes a customer, providing to the customer device an access code for activation, receiving a request from the customer device for the digital identification, where the request includes the access code and customer information that describes the customer, providing a request for secure information that describes the customer from a secure information database, receiving the secure information that describes the customer stored in the secure information database, generating the digital identification for the customer based on the secure information and the customer information, and providing the digital identification to the customer device.

Abstract: A method for creating an identification document that includes: defining a debossed region on a surface of a card blank, the debossed region having a pre-determined pattern being indented into the card blank; and applying, as part of a lamination process, an overlay on the surface of the card blank to cover the defined debossed region such that an air gap is formed on the card blank's surface during the lamination process and is sealed and removed after the lamination process, and that a tactile pattern thus created on the surface of the overlay substantially duplicates the pre-determined pattern of the defined debossed region.

Abstract: Some implementations may provide a machine-assisted method for determining a trustworthiness of a requested transaction, the method including: receiving, from a relying party, a request to determine a trustworthiness of a particular transaction request, the transaction request initially submitted by a user to access data managed by the relying party; based on the transaction request, summarizing the particular transaction request into transactional characteristics, the transactional characteristics devoid of source assets of the transaction, the source assets including credential information of the user, the credential information of the relying party, or information content of the requested transaction; generating first machine-readable data encoding transactional characteristics of the underlying transaction as requested, the transactional characteristics unique to the particular transaction request; submitting a first inquiry at a first engine to determine an access eligibility of the user submitting the t

Abstract: A machine-assisted method for verifying a video presence that includes: receiving, at a computing device of an identity provider, an authentication request initially sent from a requester to access an account managed by a relying party, different from the identity provider; retrieving, from the authentication request, at least a portion of a video stream feed initially from the requester, to the computing device, the portion of video stream feed portraying a face of the requester; extracting the face of the requester from the portion of the video stream feed; providing a directive to the requester soliciting a corresponding gesture; and receiving a response gesture from the requester.

Abstract: A computer-implemented method includes: receiving a request for associating a first index of privileges and permissions with an identity token, the first index specifically encoding the privileges and permissions of a first subscriber in accessing transactional data of the requester, the request including the identity token that identifies a person and has been issued to the requester by a trusted entity through a vetting process; in response to determining that the identity token is valid and verifying that the requester is the person identified by the identity token, associating the first index of privileges and permissions of the first subscriber with the identity token; and providing the identity token associated with the first index of privileges and permissions of the first subscriber, the identity token enabling the first subscriber to access transactional data of the requester in accordance with the first index of privileges and permissions.

Abstract: Some implementations may include a method for watermarking an identification document, the method including: receiving a digitally watermarked digital facial portrait of the person, the digital facial portrait embedded with at least one digital watermark identifying payload data linking the digital facial portrait to the person portrayed in the digital facial portrait; receiving results of comparison between the digital facial portrait of the person and the person presenting the digitally watermarked digital facial portrait; retrieving the at least one digital watermark in response to receiving comparison results that the person portrayed in the digital facial portrait is the person presenting the digitally watermarked digital facial portrait; and determining that the digital facial portrait is authentic based on the retrieved at least one digital watermark.

Abstract: A machine-assisted method for verifying a video presence that includes: receiving, at a computing device of an identity provider, an authentication request initially sent from a requester to access an account managed by a relying party, different from the identity provider; retrieving, from the authentication request, at least a portion of a video stream feed initially from the requester, to the computing device, the portion of video stream feed portraying a face of the requester; extracting the face of the requester from the portion of the video stream feed; providing a directive to the requester soliciting a corresponding gesture; and receiving a response gesture from the requester.

Abstract: A computer-assisted method includes: accessing information encoding a high-resolution image of an identification document, the high-resolution image captured from a camera of a mobile computing device; extracting personally identifiable information (PII) printed on more than one locations on the front of the identification document; correlating the PII to determine a first authentication factor; inspecting the high-resolution image to detect at least one fine-print feature from a substrate of the identification document, the at least one fine-print feature not detectable by naked eyes alone and without a visual aid; in response to (i) determining a match for the PII and (ii) determining that at least one fine-print feature is present, correlating the PII with information content from the at least one fine-print feature; and in response to determining that the PII are correlated with information content from the at least one fine-print feature that the identification document as authentic.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for facial recognition using fractal features are disclosed. In one aspect, a method includes the actions of accessing data encoding a facial image, the facial image including a face. The actions further include generating a hierarchical graphical model of the face in the facial image, the hierarchical graphical model including more than nodes from at least one level, each level approximating the face within a contour. The actions further include applying a bank of filters to the face at a particular node, each filter spanning more than one scale and at least one direction. The actions further include analyzing filter responses from the bank of filters applied at each direction to obtain a similarity measure that consolidates filter responses from filters applied at more than one scale. The actions further include generating a vector representation.

Abstract: Personal data may be embedded in a kinegram of an identification document using a suitable low energy laser without compromising the integrity of the kinegram or the identification document. The personal data can be written in a metalized portion of the kinegram in a high definition, high resolution manner such that the personal data may be read by a human without the use of a text-enhancing viewer device (e.g., magnifying glasses). Additional personal data can be written in a reduced text size (e.g., micro-text) in another metalized portion of the kinegram such that a human must use a text-enhancing viewer device to view the micro-text personal data.

Abstract: A system and method for determining whether an eye image includes a left eye or a right eye image is described. After obtaining an eye image, the centers of the iris and pupil in the eye image are located. A horizontal displacement between the centers of the iris and pupil is determined. In addition, neural network classifiers are used to perform eye corner detection to identify inner and outer eye corners in the image. A determination is made as to whether the eye image includes a left eye image or a right eye image based on the detected eye corners and horizontal displacement.

Abstract: Some implementations may provide a method for generating a portrait of a subject for an identification document, the method including: receiving a photo image of the subject, the photo image including the subject's face in a foreground against an arbitrary background; determining the arbitrary background of the photo image based on the photo image alone and without user intervention; masking the determined background from the photo image; and subsequently generating the portrait of the subject for the identification document of the subject, the portrait based on the photo image with the determined background masked.

Abstract: Methods, systems, and computer-readable storage mediums for detecting facial liveliness are provided. Implementations include actions of processing a facial image of a subject to determine a corneal reflection of an illuminator adjacent to the subject, the facial image being captured at a time point, determining an expected corneal reflection of the illuminator based on an illumination of the illuminator at the time point, comparing the determined corneal reflection of the illuminator to the expected corneal reflection of the illuminator to obtain a comparison result, and determining facial liveliness of the subject based on the comparison result.

Abstract: First data corresponding to a first document is obtained. A first feature vector is generated for the first data. The first feature vector is provided as an input to a classifier. The classifier is trained to characterize the first document as having one of a first characteristic or a second characteristic based on the first feature vector.

Abstract: A method for creating an identification document that includes: defining a debossed region on a surface of a card blank, the debossed region having a pre-determined pattern being indented into the card blank; and applying, as part of a lamination process, an overlay on the surface of the card blank to cover the defined debossed region such that an air gap is formed on the card blank's surface during the lamination process and is sealed and removed after the lamination process, and that a tactile pattern thus created on the surface of the overlay substantially duplicates the pre-determined pattern of the defined debossed region.