US 11,921,818 B2
Image recognition method and apparatus, image preprocessing apparatus, and method of training neural network
Jang-Hyun Kim, Seoul (KR); Hyun Oh Song, Seoul (KR); Wonho Choo, Seoul (KR); Seungyong Moon, Seoul (KR); Gaon An, Seoul (KR); and Hosan Jeong, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR); and Seoul National University R&DB Foundation, Seoul (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR); and Seoul National University R&DB Foundation, Seoul (KR)
Filed on May 26, 2021, as Appl. No. 17/330,495.
Claims priority of application No. 10-2020-0165958 (KR), filed on Dec. 1, 2020.
Prior Publication US 2022/0171999 A1, Jun. 2, 2022
Int. Cl. G06F 18/214 (2023.01); G06V 10/50 (2022.01); H04N 1/60 (2006.01)
CPC G06F 18/2148 (2023.01) [G06V 10/50 (2022.01); H04N 1/6063 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A processor-implemented method comprising:
obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space;
obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and
obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.