A user authentication method and a user authentication apparatus acquire an input image including a frontalized face of a user, calculate a confidence map including confidence values, for authenticating the user, corresponding to pixels with values maintained in a depth image of the frontalized face of the user among pixels included in the input image, extract a second feature vector from a second image generated based on the input image and the confidence map, acquire a first feature vector corresponding to an enrolled image, and perform authentication of the user based on a correlation between the first feature vector and the second feature vector.

An operating method of a server, comprising, mediating a video call session between a first terminal and a second terminal; receiving satisfaction information on the video call session of a user of the first terminal from the first terminal; preparing combination of a specific type of personal information about a user of the first terminal and facial characteristic information about a user of the second terminal; calculating a correlation between the combination and the satisfaction information corresponding to the combination; receiving a video call mediating request from a third terminal and from a plurality of candidate terminals, and predicting satisfaction information of a user of the third terminal with respect to each of the candidate terminals; and choosing a fourth terminal among the candidate terminals.

Systems, apparatus, articles of manufacture, and methods for eye gaze correction in camera image streams are disclosed. An example apparatus disclosed herein includes timing circuitry to calculate a duration of time for which an eye gaze of a first user of a video conference is directed toward a second user of the video conference, the second user presented as an image via a video conference interface, the video conference interface presented by a display of an electronic device, and social feedback control circuitry to select an eye gaze time threshold based on content associated with the video conference interface, and in response to the duration satisfying the eye gaze time threshold, cause an alert to be presented on the display with the video conference interface.

An image processing method includes receiving an image frame, detecting a face region of a user in the image frame, aligning a plurality of preset feature points in a plurality of feature portions included in the face region, performing a first check on a result of the aligning based on a first region corresponding to a combination of the feature portions, performing a second check on the result of the aligning based on a second region corresponding to an individual feature portion of the feature portions, redetecting a face region based on a determination of a failure in passing at least one of the first check or the second check, and outputting information on the face region based on a determination of a success in passing the first check and the second check.

The subject technology receives image data including a representation of a physical item. The subject technology analyzes the image data to determine an object corresponding to the physical item. The subject technology identifies a set of colors corresponding to a set of regions of the determined object. The subject technology analyzes second image data to detect a second object corresponding to a representation of a particular body part of a user. The subject technology generates augmented reality content based at least in part on the identified set of colors and the detected second object. The subject technology causes display, at a client device, the augmented reality content applied to the detected second object.

The present invention generally relates to an emotion recognition and notification system comprises an input unit includes a camera for capturing a facial image of a user's face; a pre-processing unit to remove noise and enhance the details of the captured facial image; a face detection unit to detect a face from the captured facial image; a features extraction unit to extract a set of image features from detected face from the captured facial image; a central processing unit equipped with a two channel facial expression recognition network based on CNN and LSTM to recognize an emotion of a user upon comparing the set of image features from a pre-stored image features; and a control unit equipped with a communication module to alert a registered user about a recognized emotion.

Systems and methods used to perform touchless registration of images for surgical navigation are disclosed. In some embodiments, the systems include a 3-D scanning device to capture spatial data of a region of interest of a patient and a reference frame. A digital mesh model is generated from the spatial data. A reference frame model is registered with the digital mesh model. Anatomical features of the digital mesh model and a patient registration model are utilized to register the digital mesh model with the patient registration model. A position of a surgical instrument is tracked relative to the reference frame and the patient registration model.

A method for training a deep learning network for face recognition includes: utilizing a face landmark detector to perform face alignment processing on at least one captured image, thereby outputting at least one aligned image; inputting the at least one aligned image to a teacher model to obtain a first output vector; inputting the at least one captured image a student model corresponding to the teacher module to obtain a second output vector; and adjusting parameter settings of the student model according to the first output vector and the second output vector.

A method includes receiving a video signal that comprises a time series of images of a face of a human, wherein the images in the time series of images comprise a set of landmark points in the face, applying tracking processing to the video signal to reveal variations over time of at least one image parameter at the set of landmark points in the human face, generating a set of variation signals indicative of variations revealed at respective landmark points in the set of landmark points, applying processing to the set of variation signals, the processing comprising artificial neural network processing to produce a reconstructed PhotoPletysmoGraphy (PPG) signal, and estimating a heart rate variability of a variable heart rate of the human as a function of the reconstructed PPG signal.

A processor-implemented image normalization method includes extracting a first object patch from a first input image and extracting a second object patch from a second input image based on an object area that includes an object detected from any one or any combination of the first input image and the second input image, determining, based on a first landmark detected from the first object patch, a second landmark of the second object patch; and normalizing the first object patch and the second object patch based on the first landmark and the second landmark.