A facial verification method includes separating a query face image into color channel images of different color channels, obtaining a multi-color channel target face image with a reduced shading of the query face image based on a smoothed image and a gradient image of each of the color channel images, extracting a face feature from the multi-color channel target face image, and determining whether face verification is successful based on the extracted face feature.

An eye tracking device for tracking an eye is described. The eye tracking device comprises: a first diffractive optical element, DOE, arranged in front of the eye, an image module, wherein the image module is configured to capture an image of the eye via the first DOE. The first DOE is adapted to direct a first portion of incident light reflected from the eye, towards the image module. The eye tracking device is characterized in that the first DOE is configured to provide a lens effect.

An information processing apparatus (100) includes an acquisition unit (122) that acquires a first image from which person region feature information regarding a region including other than a face of a retrieval target person is extracted, a second image in which a collation result with the person region feature information indicates a match, and a facial region is detected, and result information indicating a collation result between face information stored in a storage unit and face information extracted from the facial region, and a display processing unit (130) that displays at least two of the first image, the second image, and the result information on an identical screen.

The arrangement is provided for monitoring state and sequence of movement in an aseptic work chamber of a containment standing in an installation room. At least one work glove projects into the work chamber, wherein the respective work glove is able to stretch up to a maximum grasping range in the three spatial axes in the work chamber. The arrangement comprises a tracking system, the recordings of which serve to continuously localize the at least one work glove in three dimensions and are stored in a computer unit. At least one three-dimensional or two-dimensional prohibited region, which may be adjoined by a warning region, is defined in the work chamber. Individual surface sections or the entire floor of the containment can be defined as a prohibited region. A prohibited region and possibly a warning region in front of this can be set up around machines which are installed in the work chamber and which constitute a danger for the operator. The coordinates of prohibited region and warning region are stored in the computer unit. The at least one work glove must not be used to intervene in the prohibited region and should not be used to intervene in the warning region.

A method and system for detecting children’s sitting posture based on face recognition of children are provided in the disclosure, which relates to the technical field of children’s sitting posture correction. By automatically identifying children’s ages, real-time detection and intelligent supervision can be performed on children’s sitting posture according to different ages of the children. According to the disclosure, the human bone relation information can be obtained only by simply and comprehensively calculating bone position information of several key parts of the human body, such as eyes, shoulders, nose, legs, knees, feet and the like, and then the sitting posture condition of the human body can be determined by comparing the human bone relation information with a corresponding set threshold. It is not necessary to carry out separate model training on sitting postures, but only to measure key data, which greatly decreases time and accuracy of sitting posture detection.

Aspects of the disclosure relate to a semiconductor device power management system including a semiconductor device of a set of semiconductor devices provided on a substrate, wherein the semiconductor device includes an independent power supply unit.

An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.

An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.

An electronic device is provided by the present disclosure. The electronic device includes a substrate, a light emitting diode and an optical sensor. The light emitting diode is disposed on the substrate and emits a light. The optical sensor is disposed on the substrate and is configured to receive the light, and the optical sensor receives the light to generate a first electrical signal for fingerprint authentication, and receives the light to generate a second electrical signal for luminance calibration of the light.

An action recognition method and apparatus related to artificial intelligence and include extracting a spatial feature of a to-be-processed picture, determining a virtual optical flow feature of the to-be-processed picture based on the spatial feature and X spatial features and X optical flow features in a preset feature library, where the X spatial features and the X optical flow features include a one-to-one correspondence, determining a first type of confidence of the to-be-processed picture in different action categories based on similarities between the virtual optical flow feature and Y optical flow features, where each of the Y optical flow features in the preset feature library corresponds to one action category, X and Y are both integers greater than 1, and determining an action category of the to-be-processed picture based on the first type of confidence.