US 12,299,966 B2
Information processing apparatus, information processing method, non-transitory computer-readable storage medium storing program, and system
Takayuki Yamada, Kanagawa (JP); and Shinjiro Hori, Kanagawa (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Jun. 22, 2022, as Appl. No. 17/846,161.
Claims priority of application No. 2021-107823 (JP), filed on Jun. 29, 2021.
Prior Publication US 2022/0415025 A1, Dec. 29, 2022
Int. Cl. G06V 10/776 (2022.01); G06T 7/12 (2017.01); G06V 10/22 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01)
CPC G06V 10/776 (2022.01) [G06T 7/12 (2017.01); G06V 10/22 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01); G06T 2207/20021 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
18. A system including a server and an image processing apparatus,
wherein the server comprises:
an acquisition unit configured to acquire a set of image data and label data serving as correct answer data and representing, as a label value, a region to which a pixel of the image data belongs;
an estimation unit configured to estimate, from the image data, a region to which each pixel of the image data belongs using a learning model;
a calculation unit configured to calculate an error between the label data and an estimation result by the estimation unit;
an updating unit configured to update the learning model based on the error calculated by the calculation unit; and
a transmission unit configured to transmit the learning model updated by the updating unit to the image processing apparatus,
the image processing apparatus comprises
an image processing unit configured to execute image processing using the learning model transmitted by the transmission unit,
the calculation unit calculates a first error for a boundary region of an image represented by the image data, calculates a second error for a non-boundary region different from the boundary region, and calculates the error between the label data and the estimation result based on the first error and the second error, and
an influence of the first error on the calculation by the calculation unit is controlled to be smaller than an influence of the second error on the calculation by the calculation unit.