US 12,014,529 B2
Image processing method and apparatus using neural network
Tianchu Guo, Beijing (CN); Hui Zhang, Beijing (CN); Xiabing Liu, Beijing (CN); ByungIn Yoo, Seoul (KR); ChangKyu Choi, Seongnam-si (KR); Jaejoon Han, Seoul (KR); YoungJun Kwak, Seoul (KR); and Yongchao Liu, Beijing (CN)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Jan. 20, 2021, as Appl. No. 17/153,018.
Claims priority of application No. 202010071912.3 (CN), filed on Jan. 21, 2020; and application No. 10-2020-0166879 (KR), filed on Dec. 2, 2020.
Prior Publication US 2021/0224511 A1, Jul. 22, 2021
Int. Cl. G06V 10/40 (2022.01); G06N 3/08 (2023.01); G06T 3/10 (2024.01); G06T 5/50 (2006.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 40/16 (2022.01); G06V 40/18 (2022.01)
CPC G06V 10/40 (2022.01) [G06N 3/08 (2013.01); G06T 3/10 (2024.01); G06T 5/50 (2013.01); G06V 10/809 (2022.01); G06V 10/82 (2022.01); G06V 40/168 (2022.01); G06V 40/193 (2022.01)] 24 Claims
OG exemplary drawing
 
1. An image processing method comprising:
extracting an input feature from an input image;
generating augmented features by augmenting the input feature; and
generating a prediction result based on the augmented features,
wherein the generating of the augmented features is performed using an inference operation of a trained machine learning model.