公开(公告)号：US20230214632A1

公开(公告)日：2023-07-06

申请号：US18121208

申请日：2023-03-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongbum CHOI ,  Youngjun KANG ,  Daul PARK ,  Hyunhee PARK ,  Arang LEE ,  Jonghoon WON ,  Jaemyung LEE

IPC: G06N3/0464

CPC classification number: G06N3/0464

Abstract: An electronic device may execute a neural network model for generating an image. Generating the image includes consecutively obtaining a plurality of frames by using a camera. A first frame among the plurality of frames may be presented to a first group of the neural network model, as a first input, and first result data corresponding to the first input stored in a memory. The first frame may be presented to a second group, as a second input. Upon determining that a second computation parameter of the second group is the same as a first computation parameter of the first group, the first result data is used as second result data corresponding to the second input, without performing a neural network computation that is based on the second group.

公开(公告)号：US20200244835A1

公开(公告)日：2020-07-30

申请号：US16749332

申请日：2020-01-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongbum CHOI ,  Kihuk LEE ,  Jungeun LEE ,  Hyungju CHUN ,  Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Arang LEE ,  Sungjun LIM ,  Changsu HAN

IPC: H04N1/32 ,  G06F16/583 ,  G06F16/51 ,  H04L29/08

Abstract: An electronic device is provided. The electronic device includes a housing, a wireless communication circuit, a camera configured to generate raw image data, at least one processor, and a memory. The memory stores instructions configured, when executed, to enable the processor to process first image data corresponding to raw image data via a first algorithm and generate second image data, process the first image data or the second image data via a second algorithm and generate third image data, the second algorithm being different from the first algorithm, generate a first file including the second image data and the third image data, receive priority information from an external electronic device via the wireless communication circuit, generate a second file including the second image data and the third image data based on the priority information, and transmit the second file via the wireless communication circuit to the external electronic device.

公开(公告)号：US20210019858A1

公开(公告)日：2021-01-21

申请号：US16981103

申请日：2019-03-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongbum CHOI ,  Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Arang LEE ,  Hyungju CHUN ,  Changsu HAN ,  Donghyun YEOM

IPC: G06T1/20 ,  G06T5/50 ,  G06K9/00

Abstract: An electronic device is disclosed. An electronic device according to various embodiments may comprise a memory, a communication module, and a processor, wherein the processor is configured to: identify a raw image; on the raw image, perform image processing according to a designated first image signal processing set; transmit the raw image, for which the image processing according to the designated first image signal processing set has at least partially been performed, to an external electronic device by using the communication module during the image processing; and transmit information corresponding to the at least partial processing to the external electronic device so as to allow the external electronic device to omit, by using the raw image, for which the image processing has at least partially been performed, processing corresponding to the at least partial processing among a designated second image signal processing set included in the external electronic device. Various other embodiments may be provided.

公开(公告)号：US20200302583A1

公开(公告)日：2020-09-24

申请号：US16823795

申请日：2020-03-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changsu HAN ,  Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Jungeun LEE ,  Sungjun LIM ,  Hyungju CHUN ,  Jongbum CHOI ,  Jonghun WON ,  Arang LEE

IPC: G06T5/50 ,  H04N9/73 ,  G06T3/40 ,  H04N5/265 ,  H04N5/235

Abstract: An electronic device, a method and a storage medium are disclosed. The electronic device includes a processor and a memory operatively coupled to the processor. The processor is configured to receive a user input from an external electronic device. The processor is also configured to synthesize a first region that is a first partial region of a first raw image and a second partial region of a second raw image based on the user input to generate a composite raw image. The processor is further configured to modify at least one of a first attribute of the first raw image and a second attribute of the second raw image to generate a third attribute. Additionally, the processor is configured to calibrate the composite raw image using the third attribute to generate a composite image.

公开(公告)号：US20190266756A1

公开(公告)日：2019-08-29

申请号：US16282707

申请日：2019-02-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyungju CHUN ,  Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Arang LEE ,  Jongbum CHOI ,  Changsu HAN ,  Hajoong PARK ,  Donghyun YEOM

IPC: G06T9/00 ,  G06T7/11 ,  H04N5/235

Abstract: According to an embodiment, a method may include segmenting a first image into a first block and a second block, generating first compression loss data corresponding to the first block and second compression loss data corresponding to the second block, identifying a first compression property, segmenting a second image into a third block and a fourth block and compressing the second image, wherein the compressing includes compressing the third block according to the first compression property, generating third compression loss data corresponding to the third block, when a difference between the first compression loss data and the third compression loss data meets a first predetermined condition, compressing the fourth block according to the first compression property, and when the difference meets a second predetermined condition, compressing the fourth block according to a second compression property. Other various embodiments are possible as well.

公开(公告)号：US20210044775A1

公开(公告)日：2021-02-11

申请号：US16969107

申请日：2019-02-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Arang LEE ,  Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Hyungju CHUN ,  Jongbum CHOl ,  Changsu HAN ,  Hajoong PARK ,  Donghyun YEOM

IPC: H04N5/917 ,  H04N5/232

Abstract: An electronic device is disclosed. The electronic device according to various embodiments comprises an image sensor, an image processor, and a control circuit electrically connected with the image sensor through a first interface and electrically connected with the image processor through a second interface, wherein the control circuit is configured to obtain a first image and a second image for an external object by using the image sensor through the first interface, transfer the first image to the image processor through the second interface such that the image processor determines attribute information related to correction of the first image, receive the attribute information from the image processor, compress the second image according to parameter information related to compression of the second image determined at least based on the attribute information, and transfer the compressed second image to the image processor through the second interface.

公开(公告)号：US20200322530A1

公开(公告)日：2020-10-08

申请号：US16840986

申请日：2020-04-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jongbum CHOI ,  Arang LEE ,  Sungoh KIM ,  Hyunhee PARK ,  Donghyun YEOM ,  Jonghoon WON ,  Kihuk LEE

IPC: H04N5/232 ,  H04N21/2343 ,  G06T5/50

Abstract: An electronic device and method are provided. The electronic device includes a camera, a communication circuit, and a processor configured to be operably coupled to the camera and the communication circuit. The processor is further configured to receive first image data from the camera by controlling the camera based on a first parameter, transmit the first image data to an external electronic device by using the communication circuit in response to acquisition of the first image data, identify a second parameter for controlling the camera at least based on the external electronic device having received the first image data, and acquire second image data by controlling the camera based on the second parameter in response to the identification of the second parameter.

公开(公告)号：US20200320298A1

公开(公告)日：2020-10-08

申请号：US16841741

申请日：2020-04-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungoh KIM ,  Youngjo KIM ,  Jiyoon PARK ,  Hyunhee PARK ,  Hyungju CHUN ,  Jongbum CHOI ,  Changsu HAN ,  Jonghun WON ,  Arang LEE ,  Sungjun LIM

IPC: G06K9/00 ,  G06T3/40 ,  G06K9/03 ,  H04N5/232 ,  H04N5/765 ,  H04N5/917 ,  H04N7/08

Abstract: In accordance with an aspect of the disclosure, an electronic device comprises a communication circuit; a display; at least one processor operatively connected to the display and the communication circuit; and a memory operatively connected to the at least one processor, wherein the memory stores instructions that, when executed, cause the at least one processor to perform a plurality of operations comprising: storing first raw image data in the memory; generating first small raw image data smaller in size than the first raw image data, from the first raw image data; transmitting the first small raw image data to a first external electronic device via the communication circuit; receiving information about an object region for identifying at least one object of the first small raw image data from the first external electronic device via the communication circuit; transmitting a first region of the first raw image data to a second external electronic device via the communication circuit based on a user input and the information about the object region; displaying first display image data corresponding to the information about the object region via the display; and identifying the user input associated with selection of the object region.

公开(公告)号：US20230186480A1

公开(公告)日：2023-06-15

申请号：US18105519

申请日：2023-02-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungju CHUN ,  Youngjo KIM ,  Hyunhee PARK ,  Arang LEE ,  Sungjun LIM ,  Jongbum CHOI ,  Changsu HAN

IPC: G06T7/11 ,  G06T7/174 ,  G06T3/40

CPC classification number: G06T7/11 ,  G06T7/174 ,  G06T3/40 ,  G06T2207/20081

Abstract: A method for image segmentation based on deep learning in an electronic device includes: acquiring, by a processor of the electronic device, an input image, converting, by the processor, the input image into a first image having a first resolution and a second image having a second resolution, performing, by the processor, first image processing for the first image using a first deep learning engine, performing, by the processor, second image processing for the second image using a second deep learning engine different from the first deep learning engine, and providing, by the processor, region segmentation information of the input image based on first region segmentation information associated with the first image processing and second region segmentation information associated with the second image processing.

公开(公告)号：US20210306624A1

公开(公告)日：2021-09-30

申请号：US17057760

申请日：2019-06-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sungoh KIM ,  Youngjo KIM ,  Hyunhee PARK ,  Arang LEE ,  Hyungju CHUN ,  Jongbum CHOI ,  Changsu HAN ,  Donghyun YEOM

IPC: H04N19/11 ,  H04N19/176 ,  H04N5/232 ,  H04N19/167

Abstract: Various embodiments provide an electronic device and a method for controlling an operation of the electronic device. An electronic device according to various embodiments of the present invention may comprise: a lens unit; an image sensor; a memory used for intra-prediction of an image captured using the image sensor, and storing direction modes differently configured according to characteristics of a partial area of the lens unit; and a processor, wherein the processor: acquires a raw image corresponding to an external object by using the image sensor; divides the raw image into multiple blocks; selects a block, on which intra-prediction is to be performed, from among the multiple blocks; determines a direction mode to be used for intra-prediction of the selected block on the basis of a distortion parameter of a partial area of the lens unit corresponding to the selected block; performs the intra-prediction on the selected block on the basis of the determined direction mode; and generates a compressed image corresponding to the raw image on the basis of a result of the intra-prediction. In addition, various embodiments are possible.