Example image processing methods, apparatus/systems and articles of manufacture are disclosed herein. An example apparatus includes an image recognition application to identify matches between stored patterns and objects detected in a shelf image, where the shelf image has a shelf image scale estimate. The example apparatus further includes a scale corrector to calculate deviation values between sizes of (A) a first set of the objects detected in the shelf image and (B) a first set of the stored patterns matched with the first set of the objects and reduce an error of the shelf image scale estimate by calculating a scale correction value for the shelf image scale estimate based on the deviation values.

A fingerprint authentication device includes: a sensor unit configured to output a sensing signal by sensing a fingerprint; an image processing unit configured to generate a fingerprint image based on the sensing signal; a storage unit configured to store a template including an enrolled image; and a learning unit configured to generate a first pseudo image and add the first pseudo image to the template.

In one embodiment, a method includes determining characteristics of one or more areas in an image by analyzing pixels in the image, computing a sampling density for each of the one or more areas in the image based on the characteristics of the one or more areas, generating samples corresponding to the image by sampling pixels in each of the one or more areas according to the associated sampling density, and providing the samples to a machine-learning model as an input, where the machine-learning model is configured to reconstruct the image by processing the samples.

Device, system, and method of generating a reduced-size volumetric dataset. A method includes receiving a plurality of three-dimensional volumetric datasets that correspond to a particular object; and generating, from that plurality of three-dimensional volumetric datasets, a single uniform mesh dataset that corresponds to that particular object. The size of that single uniform mesh dataset is less than ¼ of the aggregate size of the plurality of three-dimensional volumetric datasets. The resulting uniform mesh is temporally coherent, and can be used for animating that object, as well as for introducing modifications to that object or to clothing or garments worn by that object.

A phase estimation method estimates the phase of signal components using a point spread function. The method obtains a point spread function that expresses complex frequencies at a non integer location in terms of integral frequencies, for a complex frequency of a signal at a non integer location in a complex frequency domain. It obtains complex frequencies of the signal for the integral frequencies, and computes a sum of products of the complex frequencies of the signal at the integral frequencies with the corresponding complex values of the point spread function to provide an estimate of phase of the signal at the non integer location.

A method for enforcing smoothness constraints on surface meshes produced by a Graph Convolutional Neural Network (GCNN) including the steps of reading image data from a memory, the image data including two-dimensional image data representing a three-dimensional object or a three-dimensional image stack of the three-dimensional object, performing a GCNN mesh deformation step on the image data to obtain an approximation of a surface of the three-dimensional object, the surface represented by triangulated surface meshes, at least some vertices of the triangulated surface meshes having a different number of neighboring vertices compared to other vertices in a same triangulated surface mesh, and performing a deep active surface model (DASM) transformation step on the triangulated surface meshes to obtain a corrected representation of the surface of three-dimensional object to improve smoothness of the surface.

Methods and systems are provided for electronic authentication. A modified electronic image is generated by altering at least a pixel of an electronic image. The electronic image is an image that has been previously viewed by a user during a setup process. In response to receiving an authentication request from the user, the modified electronic image is displayed to the user via an electronic display along with one or more other electronic images. A determination is made as to whether the user is able to recognize the modified electronic image. In response to determination that the user is able to recognize the modified electronic image, the authenticating request is granted.

Embodiments of this application disclose a face detection method and apparatus, a service processing method, a terminal device, and a storage medium. The method can include obtaining a to-be-detected target facial image, and performing a hierarchical fitting training by using a face alignment algorithm and a sample data set to obtain a target face alignment model. Further, the method can include invoking the target face alignment model to perform a face alignment detection on the target facial image, to obtain a target key point set of the target facial image, and determining a feature area of the target facial image according to the target key point set.

The location of a user's head, for purposes such as head tracking or motion input, can be determined using a two-step process. In a first step, at least one image is captured including a representation of at least a portion of the person, such as a head portion of the person. In a second step, a contour of the head portion can be determined, and a two-dimensional model, for example, an ellipse or other similar shape can be used to approximate the head portion of the person represented in the image. The ellipse, for example, can be modeled using a number of shapes, such as rectangles, and the portion of the person can be tracked by locating an ellipse that bounds a maximum intensity gradient of pixel values in each one of a series of images.

A time series of image frames in an anatomical scan is segmented. An image frame k in the time series of image frames is manually segmented. A non-rigid registration is then performed between the image frame k and a next image frame k+1 in the time series of image frames. A segmentation on the image frame k+1 is computed based on the non-rigid registration. Each subsequent image frame k+n in the time series of image frames is iteratively segmented using non-rigid registration with the segmented previous image frame k+(n−1) in the time series of image frames.