知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.014 seconds)

    Image region segmentation method and system using self-spatial adaptive normalization
    1.
    发明授权
    Image region segmentation method and system using self-spatial adaptive normalization 有权

    公开(公告)号：US11605167B2

    公开(公告)日：2023-03-14

    申请号：US17126299

    申请日：2020-12-18

    Applicant: Korea Electronics Technology Institute

    Inventor： Choong Sang Cho ,  Charles Hyok Song ,  Young Han Lee

    IPC: G06T7/11 ,  H04N19/167 ,  H04N19/176

    Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

    Method for audio synthesis adapted to video characteristics
    3.
    发明授权
    Method for audio synthesis adapted to video characteristics 有权

    公开(公告)号：US10923106B2

    公开(公告)日：2021-02-16

    申请号：US16256835

    申请日：2019-01-24

    Applicant: Korea Electronics Technology Institute

    Inventor： Jong Yeol Yang ,  Young Han Lee ,  Choong Sang Cho ,  Hye Dong Jung

    IPC: G10L13/00 ,  G10L13/10 ,  H04N21/233 ,  G06K9/00

    Abstract: An audio synthesis method adapted to video characteristics is provided. The audio synthesis method according to an embodiment includes: extracting characteristics x from a video in a time-series way; extracting characteristics p of phonemes from a text; and generating an audio spectrum characteristic St used to generate an audio to be synthesized with a video at a time t, based on correlations between an audio spectrum characteristic St-1, which is used to generate an audio to be synthesized with a video at a time t−1, and the characteristics x. Accordingly, an audio can be synthesized according to video characteristics, and speech according to a video can be easily added.

    Image segmentation method and system using GAN architecture
    5.
    发明授权
    Image segmentation method and system using GAN architecture 有权

    公开(公告)号：US12086712B2

    公开(公告)日：2024-09-10

    申请号：US17512463

    申请日：2021-10-27

    Applicant: Korea Electronics Technology Institute

    Inventor： Choong Sang Cho ,  Young Han Lee

    IPC: G06T7/11 ,  G06F18/21 ,  G06N3/045 ,  G06N3/08 ,  G06V10/75

    CPC classification number: G06N3/08 ,  G06F18/2163 ,  G06F18/217 ,  G06N3/045 ,  G06T7/11 ,  G06V10/751 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: There are provided a method and a system for image segmentation utilizing a GAN architecture. A method for training an image segmentation network according to an embodiment includes: inputting an image to a first network which is trained to output a region segmentation result regarding an input image, and generating a region segmentation result; and inputting the region segmentation result generated at the generation step and a ground truth (GT) to a second network, and acquiring a discrimination result, the second network being trained to discriminate inputted region segmentation results as a result generated by the first network and a GT, respectively; and training the first network and the second network by using the discrimination result. Accordingly, region segmentation performance of a semantic segmentation network regarding various images can be enhanced, and a very small image region can be exactly segmented.

    Method for separating audio sources and audio system using the same
    7.
    发明授权
    Method for separating audio sources and audio system using the same 有权
    用于分离音频源和使用其的音频系统的方法

    公开(公告)号：US09466312B2

    公开(公告)日：2016-10-11

    申请号：US14553188

    申请日：2014-11-25

    Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

    Inventor： Choong Sang Cho ,  Je Woo Kim ,  Byeong Ho Choi ,  Hwa Seon Shin

    IPC: H04R5/04 ,  G10L21/0272

    CPC classification number: G10L21/0272

    Abstract: A method for separating audio sources and an audio system using the same are provided. The method introduces the concept of a residual signal to separate a mixed audio signal into audio sources, and separates an audio signal corresponding to at least two of the audio sources as a residual signal and processes the audio signal separately. Therefore, audio separation performance can be improved. In addition, the method re-separates a separated residual signal and adds the separated residual signals to corresponding audio sources. Therefore, audio sources can be separated more safely.

    Abstract translation: 提供了一种用于分离音频源的方法和使用其的音频系统。 该方法引入残留信号的概念以将混合音频信号分离成音频源，并且将与至少两个音频源相对应的音频信号分离为残差信号并分别处理音频信号。 因此，可以提高音频分离性能。 此外，该方法重新分离分离的残差信号，并将分离的残留信号添加到相应的音频源。 因此，音频源可以更安全地分离。

    METHOD FOR ELIMINATING HOLOGRAM DC NOISE AND HOLOGRAM DEVICE USING THE SAME
    8.
    发明申请
    METHOD FOR ELIMINATING HOLOGRAM DC NOISE AND HOLOGRAM DEVICE USING THE SAME 审中-公开
    用于消除HOLOGRAM DC噪声和HOLOGRAM器件的方法

    公开(公告)号：US20130329268A1

    公开(公告)日：2013-12-12

    申请号：US13907561

    申请日：2013-05-31

    Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

    Inventor： Choong Sang Cho ,  Byeong Ho Choi ,  Hoon Jong Kang ,  Sang Keun Lee

    IPC: G03H1/08

    CPC classification number: G03H1/08 ,  G03H1/0866 ,  G03H2001/0825

    Abstract: A method for eliminating hologram DC noise and a hologram device using the same are provided. The method for processing the hologram includes: receiving input of hologram data; and implementing a differential operation with respect to the hologram data. Accordingly, the hologram data is processed by implementing the differential operation with respect to the hologram data, so that DC noise occurring when the hologram is reconstructed can be effectively eliminated.

    Abstract translation: 提供消除全息图直流噪声的方法和使用该方法的全息装置。 用于处理全息图的方法包括：接收全息图数据的输入; 并执行关于全息图数据的差分操作。 因此，通过实施相对于全息图数据的差分操作来处理全息图数据，从而可以有效地消除当重建全息图时出现的DC噪声。

    Method and system for automatic image caption generation
    9.
    发明授权
    Method and system for automatic image caption generation 有权

    公开(公告)号：US10726289B2

    公开(公告)日：2020-07-28

    申请号：US16043338

    申请日：2018-07-24

    Applicant: Korea Electronics Technology Institute

    Inventor： Bo Eun Kim ,  Choong Sang Cho ,  Hye Dong Jung ,  Young Han Lee

    IPC: G06K9/46 ,  G06T7/00 ,  G06N5/04 ,  G06N3/08 ,  G06F40/20 ,  G06F40/169 ,  G06N3/04 ,  G06N5/02

    Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

Patent Agency Ranking