Title:
ELECTRONIC DEVICE FOR RECOGNIZING TEXT IN IMAGE AND METHOD FOR OPERATING SAME
Document Type and Number:
WIPO Patent Application WO/2023/128348
Kind Code:
A1
Abstract:
An electronic device for recognizing text and a method for operating same are provided. The method may comprise the steps of: detecting positions of text fragments constituting text in an image; generating cropped images by cropping regions corresponding to the text fragments in the image; recognizing characters in the text fragments on the basis of the cropped images; generating a sentence by inputting the positions of the text fragments and the characters in the text fragments into a multimodal language model, wherein the multimodal language model is an artificial intelligence model that infers an original sentence from the text; and displaying the sentence.
Inventors:
KIM YOUNGUK (KR)
KIM KYUNGSU (KR)
KWON OHJOON (KR)
KIM YEHOON (KR)
KIM HYUNHAN (KR)
KIM HYOSANG (KR)
LEE HYUNGMIN (KR)
KIM KYUNGSU (KR)
KWON OHJOON (KR)
KIM YEHOON (KR)
KIM HYUNHAN (KR)
KIM HYOSANG (KR)
LEE HYUNGMIN (KR)
Application Number:
PCT/KR2022/019570
Publication Date:
July 06, 2023
Filing Date:
December 05, 2022
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06V30/14; G06N3/045; G06V10/774; G06V10/82; G06V30/262
Foreign References:
US20210201182A1 | 2021-07-01 | |||
KR102144464B1 | 2020-08-14 | |||
KR20210109145A | 2021-09-06 | |||
KR20200087225A | 2020-07-20 | |||
KR20190021146A | 2019-03-05 |
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: