A method and a system for measuring a feature of persons. The method includes defining the feature of persons being measured. The method further includes measuring values of data points from a sample of digital images comprising the persons, according to the defined feature by a first algorithm. The method further includes generating a distribution curve of the measured values. The method further includes standardizing the measured values by implementing a hyperbolic tangent function transformation.

Various embodiments set forth systems and techniques for training a landmark model. The techniques include determining, using the landmark model, a first landmark in a set of first landmarks associated with a first image; performing, on the first image, a first perturbation to obtain a second image; determining, using the landmark model, a second landmark in a set of second landmarks associated with the second image; determining, based on a first distance between the first landmark and the second landmark, a first loss function; and updating, based on the first loss function, a first parameter of the landmark model.

A method of presenting product information in a vending machine may include detecting audio information from a consumer and converting the audio information to a text string. The method may include identifying a keyword in the text string, and determining products from a product database associated with the keyword. The method may include returning a list of the products that correspond to the keyword.

A system and method for determining a facial expression including a facial mask generator arranged to detect a plurality of facial points from one or more facial images to generate one or more associated facial point masks, arranged to represent the facial features of an associated face of the one or more facial images; and a learning network arranged to receive and input of the one or more facial images and the one or more associated facial point masks to obtain a classification result for each of the one or more facial images, wherein the classification result is one of a plurality of predefined facial expressions.

A device, method and system for controlling an access point based on movement trends of a mover is provided. A device receives images from a camera device, the camera device configured to image a region adjacent an access point, the access point initially in a first state that prevents access therethrough. The device identifies a designator of a mover in the images. The device determines, using the designator in the images, direction vectors of the mover. The device determines a trend of movement of the mover, relative to the access point, based on changes in one or more of slope and angle of the direction vectors of the mover. The device, in response to determining that the mover is trending towards the access point, changes the access point from the first state to a second state that provides access therethrough.

There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining video data, detecting at least one face from at least one frame of the video data, determining a set of facial landmark features of the at least one face from the at least one frame of the video data, and coding the video data at least partly by a neural network based on the determined set of facial landmark features.

A digital makeup artist system includes a mobile device, a database system storing cosmetic routine information, common makeup looks, cosmetic products for skin types and ethnicity, and user look preferences of a user. The mobile device includes a user interface for interacting with a digital makeup artist. The digital makeup artist performs an interactive dialog with the user in order to capture needs of the user, including types of makeup look, indoor or outdoor look, skin condition, facial problem areas, favorite facial features. The computation circuitry analyzes the user's face image to identify face parts, analyzes the face image to determine facial characteristics, and generates image frames to be displayed in synchronization with the interaction with the digital makeup artist based on the analyzed face image, needs of the user, the stored cosmetic routine information, common makeup looks, cosmetic products for skin types and ethnicity, and the user look preferences.

A method for calibrating an animation includes obtaining a static source image of a source face; capturing, by an image capturing device, a driving video of a human; determining whether a driving face, of the human, is present in each of the video frames; measuring a driving face position and a driving face size in a calibration reference frame of the driving video; generating each of one or more modified video frames based on the calibration reference frame and each of one or more subsequent video frames; and outputting, for each of the driving video frames, the source image in response to determining that the driving face is not present, and outputting the source image and the modified video frame in response to determining that the driving face is present.

An electronic device includes: a gaze detecting unit configured to detect a position of gaze input on an image displayed on a display unit; a subject detecting unit configured to detect from the image a subject of a specific type and a region included in the subject of the specific type; and a control unit configured to execute control so that, in a case where a position selected prior to a user operation on an operating member is not on the subject in the position of gaze input, a region corresponding to the user operation, which is included in the subject in the position of gaze input, is selected in response to the user operation, regardless of the position selected prior to the user operation.

A computing system, a method, and a computer-readable storage medium for adjusting eye gaze are described. The method includes capturing a video stream including images of a user, detecting the user's face region within the images, and detecting the user's facial feature regions within the images based on the detected face region. The method includes determining whether the user is completely disengaged from the computing system and, if the user is not completely disengaged, detecting the user's eye region within the images based on the detected facial feature regions. The method also includes computing the user's desired eye gaze direction based on the detected eye region, generating gaze-adjusted images based on the desired eye gaze direction, wherein the gaze-adjusted images include a saccadic eye movement, a micro-saccadic eye movement, and/or a vergence eye movement, and replacing the images within the video stream with the gaze-adjusted images.