公开(公告)号：US20230169709A1

公开(公告)日：2023-06-01

申请号：US17899947

申请日：2022-08-31

Applicant: Electronics and Telecommunications Research Institute

Inventor： Dong Hyuck IM ,  Jung Hyun KIM ,  Hye Mi KIM ,  Jee Hyun PARK ,  Yong Seok SEO ,  Won Young YOO

IPC: G06T11/60 ,  G06T11/40 ,  G06V40/16 ,  G06F3/04842 ,  G06F3/04845

CPC classification number: G06T11/60 ,  G06T11/40 ,  G06V40/161 ,  G06F3/04842 ,  G06F3/04845

Abstract: Provided are a face de-identification method and system and a graphical user interface (GUI) provision method for face de-identification employing facial image generation. According to the face de-identification method and system and the GUI provision method, a facial area including eyes, a nose, and a mouth in a face of a person detected in an input image is replaced with a de-identified facial area generated through deep learning to maintain the face in a natural shape while protecting the person's portrait right. Accordingly, qualitative degradation of content is prevented, and viewers' concentration on the image is increased.

公开(公告)号：US20210120355A1

公开(公告)日：2021-04-22

申请号：US17032995

申请日：2020-09-25

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hye Mi KIM ,  Jung Hyun KIM ,  Jee Hyun PARK ,  Yong Seok SEO ,  Dong Hyuck IM ,  Won Young YOO

IPC: H04S5/00 ,  G10L19/008 ,  G10L25/30

Abstract: A method for receiving a mono sound source audio signal including phase information as an input, and separating into a plurality of signals may comprise performing initial convolution and down-sampling on the inputted mono sound source audio signal; generating an encoded signal by encoding the inputted signal using at least one first dense block and at least one down-transition layer; generating a decoded signal by decoding the encoded signal using at least one second dense block and at least one up-transition layer; and performing final convolution and resize on the decoded signal.

公开(公告)号：US20240177507A1

公开(公告)日：2024-05-30

申请号：US18499717

申请日：2023-11-01

Applicant: Electronics and Telecommunications Research Institute

Inventor： Dong Hyuck IM ,  Jung Hyun KIM ,  Hye Mi KIM ,  Jee Hyun PARK ,  Yong Seok SEO ,  Won Young YOO

IPC: G06V20/70 ,  G06F40/40 ,  G06T11/00 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V20/70 ,  G06F40/40 ,  G06T11/00 ,  G06V10/774 ,  G06V10/82

Abstract: An apparatus for generating text from an image may comprise: a memory configured to store at least one instruction; and a processor configured to execute the at least one instruction, wherein the processor is further configured to generate encoding information for an image based on the image and extract text information related to content of the image based on a degree of association with the encoding information.

公开(公告)号：US20210103721A1

公开(公告)日：2021-04-08

申请号：US16696354

申请日：2019-11-26

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Dong Hyuck IM ,  Jung Hyun KIM ,  Hye Mi KIM ,  Jee Hyun PARK ,  Yong Seok SEO ,  Won Young YOO

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/20 ,  G06K9/42

Abstract: Disclosed are a learning data generation method and apparatus needed to learn animation characters on the basis of deep learning. The learning data generation method needed to learn animation characters on the basis of deep learning may include collecting various images from an external source using wired/wireless communication, acquiring character images from the collected images using a character detection module, clustering the acquired character images, selecting learning data from among the clustered images, and inputting the selected learning data to an artificial neural network for character recognition.

公开(公告)号：US20170200313A1

公开(公告)日：2017-07-13

申请号：US15241543

申请日：2016-08-19

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ki Suk LEE ,  Dae Hwan KIM ,  Hang Kee KIM ,  Hye Mi KIM ,  Ki Hong KIM ,  Su Ran PARK

IPC: G06T19/00 ,  G06K9/00 ,  H04N9/31 ,  G06T7/00 ,  G06T17/20 ,  G06T15/50 ,  G06T19/20 ,  G06K9/62

CPC classification number: G06T19/006 ,  G03B21/10 ,  G03B35/20 ,  G06F3/011 ,  G06F3/017 ,  G06F3/0304 ,  G06K9/00355 ,  G06K9/6269 ,  G06K9/627 ,  G06T17/05 ,  G06T19/20 ,  G06T2219/2004 ,  H04N9/3147 ,  H04N9/3179 ,  H04N9/3194

Abstract: An apparatus and method for providing projection mapping-based augmented reality (AR). According to an exemplary embodiment, the apparatus includes an input to acquire real space information and user information; and a processor to recognize a real environment by using the acquired real space information and the acquired user information, map the recognized real environment to a virtual environment, generate augmented content that changes corresponding to a change in space or a user's movement, and project and visualize the generated augmented content through a projector.

公开(公告)号：US20230153351A1

公开(公告)日：2023-05-18

申请号：US17681416

申请日：2022-02-25

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jee Hyun PARK ,  Jung Hyun KIM ,  Hye Mi KIM ,  Yong Seok SEO ,  Dong Hyuck IM ,  Won Young YOO

IPC: G06F16/683 ,  G10H1/00 ,  G06F16/61

CPC classification number: G06F16/683 ,  G10H1/0008 ,  G10H1/0041 ,  G06F16/61 ,  G10H2240/075 ,  G10H2210/031 ,  G10H2240/095 ,  G10H2240/141 ,  G10H2240/135 ,  G10H2250/311

Abstract: The present invention relates to an apparatus and method for identifying music in a content, The present invention includes extracting and storing a fingerprint of an original audio in an audio fingerprint DB; extracting a first fingerprint of a first audio in the content; and searching for a fingerprint corresponding to the fingerprint of the first audio in the audio fingerprint DB, wherein the first audio is audio data in a music section detected from the content.

公开(公告)号：US20190318548A1

公开(公告)日：2019-10-17

申请号：US16383895

申请日：2019-04-15

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yong Sun KIM ,  Hye Mi KIM ,  Ki Tae KIM ,  Ki Hong KIM

IPC: G06T19/20 ,  G06T7/11 ,  G06T7/246

Abstract: The present invention relates to a method and an apparatus for matching a virtual object in a virtual environment, the method including generating a point cloud of a non-rigid object, matching a low resolution virtual model to the point cloud, and implementing a high resolution model using the matched model.

公开(公告)号：US20150199824A1

公开(公告)日：2015-07-16

申请号：US14338933

申请日：2014-07-23

Applicant: Electronics and Telecommunications Research Institute

Inventor： Dae Hwan KIM ,  Jin Ho KIM ,  Dong Sik JO ,  Hang Kee KIM ,  Hye Mi KIM ,  Ki Hong KIM

IPC: G06T7/20 ,  G06T7/00

CPC classification number: G06T7/2033 ,  G06K9/00355 ,  G06T2200/04 ,  G06T2207/30196 ,  G06T2215/16

Abstract: Provided are an apparatus and method for detecting a plurality of arms and hands by using a three-dimensional (3D) image. The apparatus includes an image input unit configured to acquire a 3D image of an object, an arm detecting unit configured to detect one or more component-unit candidate regions of the object in the 3D image, and detect one or more arm regions by using arm detection feature information, extracted from each of the candidate regions, and a pattern recognition algorithm, and a hand detecting unit configured to calculate a position of a hand and a position of a wrist in each of the arm regions detected by the arm detecting unit, and detect a hand region by using the position of the hand and the position of the wrist.

Abstract translation: 提供了一种通过使用三维（3D）图像来检测多个手臂和手的装置和方法。 该装置包括被配置为获取对象的3D图像的图像输入单元，被配置为检测3D图像中的对象的一个​​或多个组件单元候选区域的臂检测单元，并且通过使用臂来检测一个或多个臂区域 从每个候选区域提取的检测特征信息和模式识别算法，以及手检测单元，被配置为计算由臂检测单元检测到的每个臂区域中的手的位置和手腕的位置， 并且通过使用手的位置和手腕的位置来检测手区域。