公开(公告)号：US20230053956A1

公开(公告)日：2023-02-23

申请号：US17718450

申请日：2022-04-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Myeongjin OH ,  Jaejung PARK ,  Hyosang KIM ,  Sukho SHIN ,  Haneul JUNG

IPC: H04N5/378 ,  H04N5/3745

Abstract: In an example embodiment, a ramp generator includes a ramp circuit that receives a first ramp enable signal from a control circuit during a first ramp period, the first ramp period including a first reset period and a first sensing period, and the ramp circuit being configured to output a first ramp signal to a correlated double sampling circuit; an emphasis circuit that increases a voltage level of the first ramp signal during the first reset period, based on a first enable signal received from the control circuit; and a pre-emphasis circuit that further increases the voltage level of the first ramp signal during a first pre-emphasis period in the first reset period, based on a second enable signal received from the control circuit.

公开(公告)号：US20230206665A1

公开(公告)日：2023-06-29

申请号：US18076787

申请日：2022-12-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Younguk KIM ,  Kyungsu KIM ,  Ohjoon KWON ,  Yehoon KIM ,  Hyunhan KIM ,  Hyosang KIM ,  Hyungmin LEE

IPC: G06V30/148 ,  G06F40/253 ,  G06F40/232 ,  G06T7/70 ,  G06V30/19

CPC classification number: G06V30/148 ,  G06F40/253 ,  G06F40/232 ,  G06T7/70 ,  G06V30/19 ,  G06T2207/20132

Abstract: A method and an electronic device for recognizing text are provided. The method includes detecting positions of pieces of text included in the text in the image, generating cropped images by cropping areas corresponding to the pieces of text in the image, recognizing characters of the pieces of text based on the cropped images, generating a sentence by inputting the positions of the pieces of text and the characters of the pieces of text to a multimodal language model, wherein the multimodal language model is an artificial intelligence (AI) model for inferring an original sentence of the text, and displaying the sentence.

公开(公告)号：US20240071115A1

公开(公告)日：2024-02-29

申请号：US18238897

申请日：2023-08-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyosang KIM ,  Younguk KIM ,  Yehoon KIM ,  Jongyeong KIM ,  Hyunhan KIM ,  Chanwon SEO ,  Hyein HYUN

IPC: G06V30/148 ,  G06V10/94 ,  G06V20/62 ,  G06V30/19

CPC classification number: G06V30/155 ,  G06V10/945 ,  G06V20/62 ,  G06V30/153 ,  G06V30/19107

Abstract: A method performed by a server, may include: obtaining an image including a first text and a second text overlapping the first text; separating a first text region corresponding to the first text from the image; extracting pixels corresponding to the first text from the first text region to obtain an undamaged portion and a damaged portion of the first text; and reconstructing the first text by inpainting the damaged portion of the first text in which the first text overlaps the second text in the image.

公开(公告)号：US20230206298A1

公开(公告)日：2023-06-29

申请号：US18148629

申请日：2022-12-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kyungsu KIM ,  Ohjoon KWON ,  Younguk KIM ,  Hyunsoo CHOI ,  Yehoon KIM ,  Hyunhan KIM ,  Hyosang KIM ,  Hyungmin LEE

IPC: G06Q30/0601 ,  G06V10/80 ,  G06V30/14

CPC classification number: G06Q30/0627 ,  G06V10/806 ,  G06V30/1444

Abstract: A method and electronic device for recognizing a product are provided. The method includes obtaining first feature information and second feature information from an image related to a product, obtaining fusion feature information based on the first feature information and the second feature information by using a main encoder model that reflects a correlation between feature information of different modalities, matching the fusion feature information against a database of the product, and providing information about the product, based on a result of the matching.