Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating, based on a portrait image, a foreground image mask to indicate foreground pixels of the portrait image; identifying a percentage of white or near white pixels in the foreground by using the foreground image mask and pixel colors in the portrait image; determining whether the percentage of white or near white pixels in the foreground is larger than a predefined threshold; in response to determining, triggering identification of edge pixels in a background of the portrait image; adjusting white background pixels to add shadows by darkening the white background pixels; and adjusting the white or near white pixels in the foreground by darkening the white or near white pixels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for liveness detection are disclosed. In one aspect, a method includes the actions of capturing video data that includes multiple video frames that each include a representation of a face of a user while activating multiple light sources according to a predetermined lighting pattern. The actions further include, for each of the multiple video frames that each include the representation of the face of the user, analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern active during capture of the respective video frame. The actions further include, based on analyzing the representation of the face of the user in the respective video frame and the respective predetermined lighting pattern, determining whether the face of the user is that of a live person or a static image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying one or more layers of a document, where at least one layer is an inner layer having a particular depth; determining a spectral feature from among multiple spectral features for application to the one or more layers of the document; determining a particular type of line segment code for application to the one or more layers of the document; and generating an identification document by: i) applying the spectral feature; and ii) applying the particular type of line segment code to the inner layer having the particular depth, wherein the particular depth is determined relative to at least one other layer of the document.

Abstract: Some implementations provide a computer-implemented method that include accessing image frames from a video sequence; detecting face of a subject in each image frame from the video sequence; detecting facial landmark features in the detected face; determining whether a sufficient number of facial landmark features and image frames have been obtained; in response to determining that a sufficient number of facial landmark features and image frames have been obtained, classifying detected facial landmark features from various detected image frames; quantifying variations of the classified facial landmark features across the detected image frames; correlating the quantified variations to a pre-determined threshold; and in response to determining that the quantified variations meet the pre-determined threshold, determining that the video sequence is from a live session.

Abstract: A document authentication system is configured to support enhanced services with advanced security features within a document and by linking information embedded in the document with a secure infrastructure.

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: A document authentication system is configured to support enhanced services with advanced security features within a document and by linking information embedded in the document with a secure infrastructure.

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 system is capable of generating identifications that include distinctive line patterns corresponding to different portions of secure customer information. In some implementations, data indicating one or more linear patterns and data indicating customer information to be embedded within an identification document is obtained. Respective subsets of the customer information are assigned to each of the one or more linear patterns. A photographic image to be included within the identification document is then modified based at least on generating a portion of the photographic image that is composed of at least one of the one or more linear patterns. The modified photographic image is then disposed on an identification document to yield embedded customer information.

Abstract: In some implementations, a system is capable of generating identifications that include distinctive line patterns corresponding to different portions of secure customer information. Data indicating an input image, and a dithering matrix representing a two-dimensional array of pixel values is obtained. Pixel values of pixels included in the input image are transformed using the dithering matrix. For each pixel within the input image, the transformation includes identifying a particular pixel value within the dithering matrix that represents a particular pixel within the input image, and adjusting an intensity value of the particular pixel based on attributes of the dithering matrix. A transformed image is generated based on the transformation and then provided for output.

Abstract: Techniques are described to embed graphical identifiers into a ghost image within a layer of laminate of an identification document. The ghost image includes optically variable media that has a first appearance when viewed from a front of the identification document in reflected light at a first angle and a second, different appearance when viewed from the front of the identification document in reflected light in a second, different angle. During the ghost image generation process, a graphical identifier can be placed on a baseline ghost image to generate an adjusted ghost image. Once the adjusted ghost image is printed onto the identification document, the graphical identifier can be viewable based on the appearance of the adjusted ghost identifier in relation to the reflected light.

Abstract: A method for producing an identification article is described. The method includes associating one or more data items with one or more line patterns, where the line patterns include one or more line segments. A particular data item is associated with at least a subset of line segments and the particular data item corresponds to an attribute of a user of the identification article. The method further includes integrating the line patterns with graphical features of the identification article. The graphical features being discernable by a human eye and the subset of line segments is indiscernible by the human eye. The method includes identifying a region of the identification article that includes the subset of line segments associated with the particular data item and associating the particular line pattern with an identifying feature of the user.

Abstract: A multilayer laminate identification document including an outer layer having a contoured surface image formed therein via laser ablation. The contoured surface image has contours based on a digital monochrome image, and has a first appearance when viewed in reflected light at a first angle and a second, different appearance when viewed in reflected light at a second, different angle. The multilayer laminate identification document is formed by generating a second digital monochrome image with continuous pixel patterns from a first digital monochrome image, and irradiating the surface of the identification document with a laser using the second digital monochrome image as a guide to form a contoured surface image in the surface of the identification document.

Abstract: In general, one innovative aspect of the subject matter described in this specification can be embodied in a computer-implemented method. The method includes, detecting, by an imaging device, the presence of an object to be imaged. The method further includes, measuring, by the imaging device, a first characteristic of the object to be imaged, and measuring, by the imaging device, a second characteristic of the object to be imaged. The method further includes, determining, by a computing device, that at least one of the first characteristic of the object or the second characteristic of the object exceeds a threshold; and in response to determining, indicating, by the computing device, whether the object to be imaged is one of a spoofed object or an actual object.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhancing skin tone in a ghost image are disclosed. In one aspect, a method includes the actions of receiving a color image. The actions further include converting the color image to a grayscale image. The actions further include generating a foreground image by removing background pixels from the grayscale image. The actions further include determining a foreground pixel value range of the pixel values of the foreground image. The actions further include generating a transfer function based on the foreground pixel value range, a minimum pixel value, and a maximum pixel value. The actions further include generating a transferred image by applying the transfer function to each pixel of the foreground image. The actions further include generating a monochrome image of the transferred image.

Abstract: A computer-implemented method includes: establishing a connection between a user device of a user and a system onboard a vehicle being driven by the user; requesting access, through the established connection, to user information on the user device; in response to a grant of access, retrieving at least a portion of the user information from the user device, the portion of user information including a digital identification document of the user that had been issued by an entity after having vetted the user, the digital identification document including a digital biometric of the user as well as a digital watermark indicating the issuing entity; and retaining, on the system onboard the vehicle, data encoding the digital identification document of the user on the vehicle such that when the vehicle is inspected by a third-party agent, the digital identification document of the user is presented to the third-party agent.

Abstract: The present invention relates to a recoil reduction air gun and a method of reducing recoil of air guns when discharging. Said recoil reduction air gun comprises a cylinder that is slidably mounted to a main body of said air gun, and a recoil reduction device that is provided between the cylinder and a stock. Said recoil reduction device further comprises a recoil reduction spring seat, a first and a second springs, and a recoil rod.

Abstract: Methods of how to build a 3D model with both surface features and internal structures are disclosed. 3D image data in a hybrid data format or other suitable data formats are first received as input and then broken down into layers of 2D data. The layers of 2D data hold various attribute information about the model, such as colors, shapes, durometer hardness, etc. The layers of data are printed on printing sheets that are specially formulated. Selected materials are also deposited on printed sheets as dictated by the 2D data. Each printed sheet is cut along the shape boundaries either before or after it has been bound to previously printed sheets. Finished sheets are then bound and processed to generate a 3D model with rich details.

Abstract: A method for converting a high resolution greyscale digital image to a color image using a low resolution digital color image of the same area or region. The low resolution color image is first registered to the high resolution greyscale image. For each pixel in the high resolution greyscale image, three color elements (red, green, blue or RGB) are calculated from the value of the pixel in the greyscale image and the color value (RGB) of the pixel at the same location in the registered color image. After this process, the high resolution greyscale image will have red, green and blue color elements (RGB) to be used and displayed as a color image.