A computer-implemented method for implementing face recognition includes receiving training data including a plurality of augmented images each corresponding to a respective one of a plurality of input images augmented by one of a plurality of variations, splitting a feature embedding generated from the training data into a plurality of sub-embeddings each associated with one of the plurality of variations, associating each of the plurality of sub-embeddings with respective ones of a plurality of confidence values, and applying a plurality of losses including a confidence-aware identification loss and a variation-decorrelation loss to the plurality of sub-embeddings and the plurality of confidence values to improve face recognition performance by learning the plurality of sub-embeddings.

An information processing method and an electronic device are provided. The method is performed by a first wearable device, where the first wearable device includes a first image collector, and the method includes: obtaining a second face image by the first image collector and receiving a first face image from the second wearable device in a case that the first wearable device and a second wearable device are in a preset positional relationship; and processing first target information from the second wearable device in a case that the first face image matches the second face image.

A face liveness detection method is provided, and includes: receiving an image transmitted by a terminal, the image including a face of an object; performing data augmentation on the image, to obtain an extended image corresponding to the image, a number of extended images corresponding to the image being more than one; performing liveness detection on the extended images corresponding to the image, to obtain intermediate detection results of the extended images, a liveness detection model used in liveness detection being obtained by performing model training on an initial neural network model according to a sample image and extended sample images corresponding to the sample image; and obtaining a liveness detection result of the object in the image after fusing the intermediate detection results of the extended images.

An image recognition method includes: obtaining a to-be-recognized image; determining whether the image is a forged image by recognizing the image through a trained generative adversarial network, the generative adversarial network including a generator and a classifier. Training the classifier includes: obtaining an original image group having a plurality of original images, and a category label of each original image. Each of the plurality of original images includes a real image and a forged image corresponding to the real image. The method includes obtaining using the classifier, for a respective original image of the plurality of original images, first-type noise corresponding to the respective original image; inputting the respective original image into the generator to obtain an output of the generator, and obtaining second-type noise corresponding to the respective original image as the output; and training the classifier using the respective original image, the first-type noise, and the second-type noise.

The present disclosure relates to the field of 3D images, and discloses a display control method for a multi-viewpoint 3D display screen, comprising: acquiring identity features of a user; and performing 3D display for the user when the identity features meet conditions. The method can conduct authentication about 3D display for the user, thereby solving a problem of a single 3D display mode, and improving flexibility of 3D display mode. The present disclosure further discloses a multi-viewpoint 3D display device, a computer-readable storage medium, and a computer program product.

A system and methods for assessing an environment are disclosed. A method includes causing a robot to transmit data to first and second user devices, causing the robot to execute a first action, and, responsive to a second instruction, causing the robot to execute a second action. At least one user device is outside the environment of the robot. At least one action includes recording a video of at least a portion of the environment, displaying the video in real time on both user devices, and storing the video on a cloud-based network. The other action includes determining a first physical location of the robot, determining a desired second physical location of the robot, and propelling the robot from the first location to the second location. Determining the desired second location is responsive to detecting a touch on a touchscreen video feed displaying the video in real time.

Present disclosure provides a method for determining if an event relates to an unauthorized subject, the method comprising: determining a likelihood of how the event is similar to at least one of: (i) at least one event of a list of events relating to the unauthorized subject and (ii) at least one of a list of events relating to an authorized subject, each event of the list of events comprising data identifying the unauthorized subject, the determination of likelihood being based on the data identifying the unauthorized subject; and determining the event to relate to the unauthorized subject in response to the determination of the likelihood.

A face authentication apparatus (50) includes an image generation unit (102) that generates a first image by capturing an image of a person, a control unit (104) that, when the first image does not satisfy a criterion for face collation, controls lighting and causes the image generation unit (102) to generate a second image by capturing an image of the person again, and a face authentication unit (52) that executes face authentication by using the second image.

A door lock control device comprises: a door lock interface for communicating with a door lock; an imaging device; a controller for processing images to be acquired through the imaging device; and a storage medium. The controller determines each of first and second objects in the images as being either authorized or unauthorized depending on whether each of the first and second objects matches authentication data read from the storage medium, and controls the door lock through a door lock interface by referring to a distance between the first and second objects determined from the images when the first object is determined as being authorized and the second object is determined as being unauthorized.

An information processing device includes: an acquisition unit that acquires a first image by capturing a subject at a first distance, and extracting, from a registered biological information group that includes biological information of a plurality of registrants, a first biological information group that contains biological information of a first person detected from the first image; and a collation unit that collates biological information of a second person detected from a second image obtained by capturing the subject at a second distance, which is shorter than the distance to the subject in the first image with the biological information included in the first biological information group.