Method and apparatus for recognizing object

    公开(公告)号:US11216694B2

    公开(公告)日:2022-01-04

    申请号:US16633825

    申请日:2018-07-11

    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.

    Media processing apparatus for multi-display system and method of operation thereof

    公开(公告)号:US10225528B2

    公开(公告)日:2019-03-05

    申请号:US14823353

    申请日:2015-08-11

    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.

    Image generating apparatus and method for generation of 3D panorama image

    公开(公告)号:US10559063B2

    公开(公告)日:2020-02-11

    申请号:US15514153

    申请日:2015-09-23

    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.

    Display apparatus and control method for adjusting the eyes of a photographed user
    9.
    发明授权
    Display apparatus and control method for adjusting the eyes of a photographed user 有权
    用于调整拍摄用户的眼睛的显示装置和控制方法

    公开(公告)号:US09536133B2

    公开(公告)日:2017-01-03

    申请号:US14150265

    申请日:2014-01-08

    CPC classification number: G06K9/00268 G06K9/00208 G06T19/00

    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 translation: 提供一种显示装置。 该显示装置包括拍摄单元,被配置为拍摄脸部的形状; 检测器被配置为检测所述脸部形状的方向和角度; 变压器被配置为混合拍摄的脸部形状和3D脸部模型,并且通过使用检测到的脸部形状的方向和角度来变换混合脸部形状; 并且输出接口被配置为输出变换的脸部形状。

    Semiconductor device with a multilayer wire
    10.
    发明授权
    Semiconductor device with a multilayer wire 有权
    具有多层导线的半导体器件

    公开(公告)号:US09331015B2

    公开(公告)日:2016-05-03

    申请号:US14103014

    申请日:2013-12-11

    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.

    Abstract translation: 半导体器件包括具有沿第一方向延伸的第一线的半导体结构,覆盖半导体结构的金属间绝缘层,穿过金属间绝缘层的通孔结构以及在第二方向上在金属间绝缘层上延伸的第二电极 相对于第一方向的预定角度,第二线通过通孔结构连接到第一线,并且包括第一和第二部分,以及从第一和第二部分中的至少一个突出的突出部分, 突出部分位于第一和第二部分的边界处。

Patent Agency Ranking