-
公开(公告)号：US11966846B2
公开(公告)日：2024-04-23
申请号：US16281737
申请日：2019-02-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sungho Kang , Hyungdal Kwon , Cheon Lee , Yunjae Lim
Abstract: An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.
-
公开(公告)号：US11430137B2
公开(公告)日：2022-08-30
申请号：US16969026
申请日：2019-03-26
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sungho Kang , Yunjae Lim , Hyungdal Kwon , Cheon Lee
Abstract: An electronic device and a control method therefor are disclosed. A method for controlling an electronic device according to the present invention comprises the steps of: receiving a current frame; determining a region, within the current frame, where there is a movement, on the basis of a prior frame and the current frame; inputting the current frame into an artificial intelligence learning model on the basis of the region where there is the movement, to obtain information relating to at least one object included in the current frame; and determining the object included in the region where there is the movement, by using the obtained information relating to the at least one object. Therefore, electronic device can rapidly determine an object included in a frame configuring a captured image.
-
公开(公告)号：US11755904B2
公开(公告)日：2023-09-12
申请号：US16970859
申请日：2019-02-20
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Hyungdal Kwon , Sungho Kang , Cheon Lee , Yunjae Lim
Abstract: The disclosure relates to an artificial intelligence (AI) system that simulates functions such as cognition and judgment of the human brain by utilizing machine learning algorithms such as deep learning and its applications. In particular, the disclosure provides a method of controlling data input and output of a fully connected network according to an artificial intelligence system and its applications, the method including receiving, from a learning circuit, an edge sequence representing a connection relationship between nodes included in a current layer of the fully connected network, generating a compressed edge sequence that compresses consecutive invalid bits among bit strings constituting the edge sequence into one bit and a validity determination sequence determining valid and invalid bits among the bit strings constituting the compressed edge sequence, writing the compressed edge sequence and the validity determination sequence to the memory, and sequentially reading the compressed edge sequences from the memory based on the validity determination sequence such that the valid bits are sequentially output to the learning circuit.
-
公开(公告)号：US11295412B2
公开(公告)日：2022-04-05
申请号：US16838650
申请日：2020-04-02
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Cheon Lee , Donghyun Kim , Yongsup Park , Jaeyeon Park , Iljun Ahn , Hyunseung Lee , Taegyoung Ahn , Youngsu Moon , Tammy Lee
Abstract: An image processing apparatus applies an image to a first learning network model to optimize the edges of the image, applies the image to a second learning network model to optimize the texture of the image, and applies a first weight to the first image and a second weight to the second image based on information on the edge areas and the texture areas of the image to acquire an output image.
-
5.发明申请APPARATUS AND METHOD FOR ENCODING DEPTH IMAGE BY SKIPPING DISCRETE COSINE TRANSFORM (DCT), AND APPARATUS AND METHOD FOR DECODING DEPTH IMAGE BY SKIPPING DCT 审中-公开用于通过跳过离散余弦变换（DCT）编码深度图像的装置和方法，以及通过跳过DCT来解码深度图像的装置和方法公开(公告)号：US20130170761A1
公开(公告)日：2013-07-04
申请号：US13729844
申请日：2012-12-28
Inventor： Ho Cheon WEY , Jae Joon Lee , Cheon Lee , Yo Sung Ho
IPC: G06K9/36
CPC classification number: G06K9/36 , H04N19/12 , H04N19/147 , H04N19/176 , H04N19/597
Abstract: An apparatus and method for encoding an image by skipping discrete cosine transform (DCT), and an apparatus and method for decoding an image by skipping the DCT. An image encoding apparatus may classify residual data into groups, and may encode the residual data using a representative value of each of the groups and group identification information that is used to identify the groups.
Abstract translation: 通过跳过离散余弦变换（DCT）对图像进行编码的装置和方法，以及通过跳过DCT来解码图像的装置和方法。 图像编码装置可以将残差数据分组为组，并且可以使用用于标识组的每个组的代表值和组标识信息对残差数据进行编码。
-
Patent Agency Ranking
6.发明授权公开(公告)号：US12175361B2
公开(公告)日：2024-12-24
申请号：US16979303
申请日：2019-03-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Cheon Lee , Sungho Kang , Hyungdal Kwon , Yunjae Lim
Abstract: The present disclosure relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, and applications therefore. Disclosed is an electronic device. The electronic device comprises: a storage unit which stores therein an artificial intelligence model trained to determine parameters for a plurality of filters used for image processing on the basis of a deep neural network (DNN); and a processor for determining, through the artificial intelligence mode, parameters for each of the plurality of filters used for image processing for an input image, and performing, through the plurality of filters, filtering of the input image on the basis of the determined parameters so as to perform image processing for the input image.
-
公开(公告)号：US12001954B2
公开(公告)日：2024-06-04
申请号：US16281737
申请日：2019-02-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sungho Kang , Hyungdal Kwon , Cheon Lee , Yunjae Lim
Abstract: An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.
-
公开(公告)号：US11836890B2
公开(公告)日：2023-12-05
申请号：US17527732
申请日：2021-11-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Cheon Lee , Donghyun Kim , Yongsup Park , Jaeyeon Park , Iljun Ahn , Hyunseung Lee , Taegyoung Ahn , Youngsu Moon , Tammy Lee
CPC classification number: G06T3/403 , G06T3/4053 , G06T7/13 , G06V10/82 , G06T2207/20081
Abstract: An image processing apparatus applies an image to a first learning network model to optimize the edges of the image, applies the image to a second learning network model to optimize the texture of the image, and applies a first weight to the first image and a second weight to the second image based on information on the edge areas and the texture areas of the image to acquire an output image.
-
公开(公告)号：US11809954B2
公开(公告)日：2023-11-07
申请号：US16281737
申请日：2019-02-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sungho Kang , Hyungdal Kwon , Cheon Lee , Yunjae Lim
Abstract: An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.
-
公开(公告)号：US11315222B2
公开(公告)日：2022-04-26
申请号：US16862958
申请日：2020-04-30
Inventor： Hyunseung Lee , MunChurl Kim , Yongwoo Kim , Jae Seok Choi , Youngsu Moon , Cheon Lee
Abstract: An image processing apparatus obtains a first output image by applying an image to a first training network model, obtains a second output image by applying the image to a second training network model, and obtains a reconstructed image based on the first output image and the second output image. The first training network model is a model that uses a fixed parameter obtained through training of a plurality of sample images, the second training network model is trained to minimize a difference between a target image corresponding to the image and the reconstructed image.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.018 seconds)
