A system processes images of documents, for example, identification documents. The system transforms an image of a document to generate an image that represent the document in a canonical form. For example, if the input image has a document that is tilted at an angle with respect to the sides of the image, the system modifies the orientation of the document to show the document having sides aligned with the sides of the image. The system stores user accounts that include user information including images. The system generates a graph of nodes that represent user accounts with edges determined based on similarity scores between user accounts. The system determines connected components of user accounts, such that each connected component represents user accounts that have a high likelihood of being duplicates.

A method of recalibrating a feature data of each channel generated by a convolution layer of a convolution neural network is provided. According to some embodiments, since an affine transformation is applied to the feature data of each channel independently of the feature data of the other channel, the overall number of parameters defining the affine transformation is minimized. As a result, the amount of computations required in performing the feature data recalibration can be reduced.

An image processing method determines a geometric transform of a suspect image by efficiently evaluating a large number of geometric transform candidates in environments with limited processing resources. Processing resources are conserved by using complementary methods for determining a geometric transform of an embedded signal. One method excels at higher geometric distortion, and specifically, distortion caused by greater tilt angle of a camera. Another method excels at lower geometric distortion, for weaker signals. Together, the methods provide a more reliable detector of an embedded data signal in image across a larger range of distortion while making efficient use of limited processing resources in mobile devices.

An optical coherence tomography (OCT) system and method for cross view imaging using at least two B-scan images transformed and coupled to each other at an angle to generate a cross view image.

A method of plane tracking comprising: capturing by a camera a reference frame of a given plane from a first angle; capturing by the camera a destination frame of the given plane from a second angle different than the first angle; defining coordinates of matching points in the reference frame and the destination frame; calculating, using the first and second angles, first and second respective rotation transformations to a simulated plane parallel to the given plane; applying an affine transformation between the reference frame coordinate on the simulated plane and the destination frame coordinate on the simulated plane; and applying a projective transformation on the simulated plane destination frame coordinate to calculate the destination frame coordinate.

Certain embodiments involve calculating a vanishing point location of an image to realistically blend multiple images. For example, a method for modifying image content based on a vanishing point location computed for a background image includes receiving the background image and classifying a set of planes in the background image. The method also includes identifying, using plane boundaries, a first set of line segments that define first convergence points. Additionally, the method includes identifying a second set of line segments that are positioned within individual planes and that define second convergence points. Further, the method includes grouping the first convergence points and the second convergence points into a cluster and computing the vanishing point location from an average of point locations in the cluster. Furthermore, the method includes manipulating a feature image overlaid on the background image to generate a blended image based on the vanishing point location.

Methods and devices for selectively presenting a virtual keyboard are provided. More particularly, a change in the operating mode of a multiple screen device from a multiple screen operating mode to a single screen operating mode, or from a single screen operating mode to a multiple screen operating mode, can be determined. Moreover, a change in the operating mode can effect a change in a presentation of a virtual keyboard. More particularly, a presentation of a virtual keyboard can be retained, where the number of screens of the device in view of the user is changed, provided an application with a keyboard focus remains in view of the user after the change in operating mode.

Disclosed is a system for performing User Interface (UI) verification of a Device Under Test (DUT). Before performing the UI verification, a set of corner markers is positioned at corners of a display frame associated to the DUT. Once the set of corner markers are positioned, an image receiving module receives a DUT image, captured by an image capturing unit, of the UI pertaining to a DUT. A skew correction module for correcting orientation of the DUT image by determining an orientation correction factor. A file configuration module for storing the orientation correction factor in a pre-configuration file when the DUT image is occupying the content greater than the predefined threshold percentage. In one aspect, the orientation correction factor may be referred while testing a UI of the DUT.

Embodiments of the present invention provide systems, methods, and computer storage media for automatically synthesizing a content-aware fill using similarity transformed patches. A user interface receives a user-specified hole and a user-specified sampling region, both of which may be stored in a constraint mask. A brush tool can be used to interactively brush the sampling region and modify the constraint mask. The mask is passed to a patch-based synthesizer configured to synthesize the fill using similarity transformed patches sampled from the sampling region. Fill properties such as similarity transform parameters can be set to control the manner in which the fill is synthesized. A live preview can be provided with gradual updates of the synthesized fill prior to completion. Once a fill has been synthesized, the user interface presents the original image, replacing the hole with the synthesized fill.

Embodiments of the present invention are directed to beautifying freeform input paths in accordance with paths existing in the drawing (i.e., resolved paths). In some embodiments of the present invention, freeform input paths of a curved format can be modified or replaced to more precisely illustrate a path desired by a user. As such, a user can provide a freeform input path that resembles a path of interest by the user, but is not as precise as desired. Based on existing paths in the electronic drawing, a path suggestion(s) can be generated to rectify, modify, or replace the input path with a more precise path. In some cases, a user can then select a desired path suggestion, and the selected path then replaces the initially provided freeform input path.