US 12,118,764 B2
Method and apparatus for processing image based on partial images
Jaehyoung Yoo, Seongnam-si (KR); Changyong Son, Anyang-si (KR); Dongwook Lee, Suwon-si (KR); Jaejoon Han, Seoul (KR); and Chang Kyu Choi, Seongnam-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Feb. 17, 2021, as Appl. No. 17/177,702.
Claims priority of application No. 10-2020-0110577 (KR), filed on Aug. 31, 2020.
Prior Publication US 2022/0067419 A1, Mar. 3, 2022
Int. Cl. G06V 10/44 (2022.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); H04N 23/611 (2023.01); H04N 23/65 (2023.01); H04N 23/667 (2023.01); H04N 23/695 (2023.01)
CPC G06V 10/44 (2022.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); H04N 23/611 (2023.01); H04N 23/651 (2023.01); H04N 23/667 (2023.01); H04N 23/695 (2023.01)] 26 Claims
OG exemplary drawing
 
1. A method of processing an image, the method comprising:
extracting a feature of a current partial processing region of an input image frame by inputting pixel data of the current partial processing region into a convolutional neural network (CNN) being a multi-head CNN (MCNN);
updating a hidden state of a recurrent neural network (RNN) for a context between the current partial processing region and at least one previous partial processing region of the input image frame by inputting the extracted feature into the RNN; and
generating an image processing result for the input image frame based on the updated hidden state,
wherein the extracting comprises extracting a plurality of intermediate features of the current partial processing region by inputting the pixel data of the current partial processing region into each of plural heads of the MCNN, and
generating an encoded feature of the current partial processing region by fusing the plurality of extracted intermediate features.