US 12,333,859 B2
Information processor performing arithmetic operation using machine learning
Teppei Oguni, Kanagawa (JP); Tatsuya Okano, Kanagawa (JP); and Kengo Akimoto, Kanagawa (JP)
Assigned to Semiconductor Energy Laboratory Co., Ltd., Atsugi (JP)
Appl. No. 17/638,359
Filed by SEMICONDUCTOR ENERGY LABORATORY CO., LTD., Atsugi (JP)
PCT Filed Aug. 25, 2020, PCT No. PCT/IB2020/057918
§ 371(c)(1), (2) Date Feb. 25, 2022,
PCT Pub. No. WO2021/044249, PCT Pub. Date Mar. 11, 2021.
Claims priority of application No. 2019-162687 (JP), filed on Sep. 6, 2019.
Prior Publication US 2022/0292880 A1, Sep. 15, 2022
Int. Cl. G06V 40/16 (2022.01); G06N 3/08 (2023.01); G06T 7/62 (2017.01); G06V 40/18 (2022.01)
CPC G06V 40/176 (2022.01) [G06N 3/08 (2013.01); G06T 7/62 (2017.01); G06V 40/193 (2022.01); G06T 2207/30201 (2013.01)] 3 Claims
OG exemplary drawing
 
1. An information processor comprising: a display unit; an imaging unit; and an arithmetic unit, wherein the arithmetic unit has a neural network system learned by a brightness of an environment, lengths of a major axis and a minor axis of each pupil, and change cycles of the lengths of a person in a first moving image, wherein the person in the first moving image is a person who has no fatigue, wherein the imaging unit is configured to obtain a second moving image comprising data on a face of a user of the information processor, wherein the arithmetic unit is configured to detect eyes of the user in the second moving image, wherein the arithmetic unit is configured to detect a pupil from each of the detected eyes, wherein the arithmetic unit is configured to calculate a length of a major axis and a length of a minor axis of each of the detected pupils, wherein the information processor is configured to infer a level of fatigue of the user based on the neural network system, wherein, when the information processor infers that the user is fatigued, the information processor is configured to display an alarm indicating that the user is fatigued on the display unit, and wherein a presence or an absence of the fatigue of the user in the second moving image is inferred from the brightness of the environment, the lengths of the major axis and the minor axis of the pupils, and change cycles of the lengths in the second moving image based on a learning result of the neural network system by the first moving image.