公开(公告)号：US11024016B2

公开(公告)日：2021-06-01

申请号：US16551987

申请日：2019-08-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungjun Lim

IPC: G06T5/00

Abstract: An image processing apparatus filters an image and obtains a signal in a threshold range as a shadow. The image processing apparatus obtains boundary information by applying boundary detection filters associated with different directions. The shadow is applied, based on the boundary information, to a portion of the input image to provide an output image with improved sharpness.

公开(公告)号：US11003951B2

公开(公告)日：2021-05-11

申请号：US16421021

申请日：2019-05-23

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SOGANG UNIVERSITY RESEARCH & BUSINESS DEVELOPMENT FOUNDATION

Inventor： Hyungjun Lim ,  Suk-Ju Kang ,  Seung Joon Lee ,  Youngsu Moon ,  Siyeong Lee ,  Sung In Cho

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/46

Abstract: An image processing apparatus is provided. The image processing apparatus includes a memory configured to store at least one instruction; and a processor configured to read the at least one instruction and configured to, according to the at least one instruction: apply a learning network model to an input image frame and acquire information on an area of interest; and acquire an output image frame by retargeting the input image frame based on the acquired information on the area of interest. The learning network model is a model that is trained to acquire the information on the area of interest in the input image frame.

公开(公告)号：US10909700B2

公开(公告)日：2021-02-02

申请号：US16580204

申请日：2019-09-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungjun Lim ,  Youngsu Moon ,  Taegyoung Ahn

IPC: G06K9/00 ,  G06T7/40 ,  G06T3/40

Abstract: An image processing apparatus and method are provided. The image processing apparatus includes: a memory configured to store at least one instruction, and a processor electrically connected to the memory, wherein the processor, by executing the at least one instruction, is configured to: apply an input image to a training network model; and apply, to a pixel block included in the input image, a texture patch corresponding to the pixel block to obtain an output image, wherein the training network model stores a plurality of texture patches corresponding to a plurality of classes classified based on a characteristic of an image, and is configured to train at least one texture patch, among the plurality of texture patches, based on the input image.