US 12,014,530 B2
Image recognition device and method
Ryou Yumiba, Tokyo (JP); Yasutaka Toyoda, Tokyo (JP); and Hiroyuki Shindo, Tokyo (JP)
Assigned to HITACHI HIGH-TECH CORPORATION, Tokyo (JP)
Appl. No. 17/286,604
Filed by HITACHI HIGH-TECH CORPORATION, Tokyo (JP)
PCT Filed Dec. 21, 2018, PCT No. PCT/JP2018/047224
§ 371(c)(1), (2) Date Apr. 19, 2021,
PCT Pub. No. WO2020/129235, PCT Pub. Date Jun. 25, 2020.
Prior Publication US 2021/0374403 A1, Dec. 2, 2021
Int. Cl. G06V 10/44 (2022.01); G06F 18/20 (2023.01); G06F 18/2113 (2023.01); G06F 18/213 (2023.01); G06N 20/00 (2019.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01); G06V 20/69 (2022.01)
CPC G06V 10/44 (2022.01) [G06F 18/2113 (2023.01); G06F 18/213 (2023.01); G06F 18/285 (2023.01); G06N 20/00 (2019.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01)] 26 Claims
OG exemplary drawing
 
1. An image recognition device, comprising:
a feature extraction learning model group that stores a plurality of feature extraction learning models;
a recall learning model group that stores a recall learning model which is paired with a feature extraction learning model among the plurality of feature extraction learning models;
a feature amount extraction unit that extracts a feature amount from input data with reference to the feature extraction learning model;
a data-to-data recall unit that outputs a recall result accompanied by dimensional compression of the feature amount with reference to the recall learning model; and
a learning model selection unit that selects the feature extraction learning model from a feature extraction learning model group under a condition that a difference between the feature amount and the recall result is minimized.