Abstract:
The present disclosure relates to an electronic device for capturing a plurality of images using a plurality of cameras, generating a left-eye-view spherical image and a right-eye-view spherical image by classifying each of the plurality of images as a left-eye-view image or a right-eye-view image, obtaining depth information using the generated left-eye-view spherical image and right-eye-view spherical image, and generating a 360 degree three-dimensional image, wherein the three-dimensional effect thereof is controlled using the obtained depth information, and an image processing method therefor.
Abstract:
Provided are an AI system for simulating functions such as recognition, determination, and so forth of human brains by using a mechanical learning algorithm like deep learning, or the like, and an application thereof. In particular, according to the AI system and the application thereof, a neural network training method includes obtaining a plurality of first images belonging to a particular category and a plurality of second images for which a category is not specified, training a neural network model for category recognition, based on the plurality of first images belonging to the particular category, recognizing at least one second image corresponding to the particular category among the plurality of second images, by using the trained neural network model, and modifying and refining the trained neural network model based on the recognized at least one second image.
Abstract:
The present disclosure relates to an artificial intelligence (AI) system for simulating functions of a human brain such as cognition and decision-making by using machine learning algorithms such as deep learning, and applications thereof. In particular, the present disclosure provides a method of recognizing an object by using an AI system and its application, including: extracting pieces of first feature information respectively regarding a plurality of images, each image including an object; generating at least one piece of second feature information representing a correlation between the plurality of images by combining together the extracted pieces of first feature information respectively regarding the plurality of images; and recognizing, based on the at least one piece of second feature information, the object included in each of the plurality of images by using a pre-generated learning network model.
Abstract:
A hub apparatus and a method are provided for selecting a device. The method includes receiving a service request; determining a sensor based on the received service request; receiving state information from a device including the determined sensor; and selecting the device based on the received state information.
Abstract:
Provided is a method, performed by a device, of recognizing content, the method including selecting a template to be used for recognizing content displayed on the device when a type of a content service that provides the content to the device is determined; capturing a screen of the device when a control signal is received by the device; determining whether the captured screen corresponds to a gateway page; determining whether the captured screen corresponds to the selected template when the captured screen corresponds to the gateway page; and generating a template corresponding to the content service, based on the captured screen, when the captured screen does not correspond to the selected template.
Abstract:
Apparatuses and methods for reproducing an image in a plurality of displays are provided. The method includes obtaining a display identifier that identifies a position of a display among the plurality of displays, based on information on an arrangement of the plurality of displays transmitted by the image reproduction control apparatus; obtaining an image segment to be reproduced in a display corresponding to the display identifier among the plurality of displays, from the image; determining the importance factor of the image segment based on at least one of the image and the viewing environment of the plurality of displays; generating an encoded image segment by encoding the image segment according to an encoding method corresponding to the importance factor; and transmitting a bitstream including the display identifier, the importance factor and the encoded image segment to the image reproduction control apparatus.
Abstract:
A method, performed by an electronic apparatus, of executing an application, based on a voice input of a user, and the electronic apparatus are provided. The method includes performing voice recognition on the voice command for executing the application, determining a target page among a plurality of pages displayable when the application is executed, based on a result of the voice recognition, generating a virtual input sequence for displaying a second screen corresponding to the target page, instead of a first screen currently displayed, and executing the application in response to the virtual input sequence.
Abstract:
Disclosed are an apparatus and a method for generating an image for generation of a 3D panorama image. A method for generating a 3D panorama image in an image generating apparatus comprises the steps of: receiving an input of a plurality of 2D images and a plurality of depth maps corresponding to the plurality of 2D images; setting a left-eye image area and a right-eye image area for each of the plurality of 2D images on the basis of the plurality of depth maps; and synthesizing images of each of the left-eye image areas that are set in the plurality of 2D images to thereby generate a left-eye panorama image and synthesizing images of each of the right-eye image areas that are set in the plurality of 2D images to thereby generate a right-eye panorama image. Accordingly, the image generating apparatus can generate a 3D panorama image without distortion on the basis of a plurality of 2D images.
Abstract:
A display apparatus is provided. The display apparatus includes a photographing unit configured to photograph the shape of a face; a detector is configured to detect a direction and angle of the face shape; a transformer is configured to mix the photographed face shape and a 3D face model and to transform the mixed face shape by using the detected direction and angle of the face shape; and an output interface is configured to output the transformed face shape.
Abstract:
A semiconductor device includes a semiconductor structure having a first wire extending in a first direction, an intermetallic insulating layer covering the semiconductor structure, a via structure penetrating the intermetallic insulating layer, and a second wire extending on the intermetallic insulating layer in a second direction at a predetermined angle with respect to the first direction, the second wire being connected to the first wire through the via structure and including first and second portions on each other, and a protruding portion protruding from at least one of the first and second portions, the protruding portion being at a boundary of the first and second portions.